Podcasts about Text mining

Process of analysing text to extract information from it

  • 56PODCASTS
  • 71EPISODES
  • 32mAVG DURATION
  • 1MONTHLY NEW EPISODE
  • Jan 15, 2025LATEST
Text mining

POPULARITY

20172018201920202021202220232024


Best podcasts about Text mining

Latest podcast episodes about Text mining

History in Focus
S3 E5 Jo Guldi on Text Mining, AI, and Digital History

History in Focus

Play Episode Listen Later Jan 15, 2025 83:30


Historian and quantitative methods expert Jo Guldi discusses text mining, AI, and the wider landscape of digital history in this longform conversation. Guldi's work on these subjects can be found in two recent AHR articles—“The Algorithm: Mapping Long-Term Trends and Short-Term Change at Multiple Scales of Time” published in the June 2022 issue and “The Revolution in Text Mining for Historical Analysis is Here” from the June 2024 issue—and in the book The Dangerous Art of Text Mining: A Methodology for Digital History published in 2023 by Cambridge University Press.

INSiDER - Dentro la Tecnologia
Gli algoritmi che ci conoscono meglio di quanto pensiamo

INSiDER - Dentro la Tecnologia

Play Episode Listen Later Dec 21, 2024 17:13 Transcription Available


Siamo ormai nel pieno delle festività natalizie e, mai come in questi giorni, siamo impegnati a cercare regali, fare acquisti o trascorrere intere serate con un tè o una cioccolata calda, guardando l'ennesimo episodio di quella serie TV che abbiamo trovato tra i contenuti consigliati su Netflix. Dai social alle pubblicità, dai negozi online alle piattaforme di streaming, tutte queste realtà hanno infatti affinato i loro algoritmi negli anni, creando un rapporto con noi utenti estremamente personalizzato e in grado di proporci contenuti che rispecchiano perfettamente i nostri gusti. In questa puntata parliamo di questi algoritmi di raccomandazione, delle diverse tipologie e del loro funzionamento, nonché del modo in cui vengono utilizzati, rispettando i diritti alla privacy sanciti da normative come il GDPR.Nella sezione delle notizie parliamo di una consultazione pubblica in Regno Unito che riguarda tra le altre cose l'utilizzo di opere coperte da diritto d'autore per addestrare le IA, della scoperta di un nuovo buco nero gigante grazie al James Webb e infine della costellazione europea per le telecomunicazioni che prenderà presto forma.--Indice--00:00 - Introduzione01:01 - Il compromesso tra IA e diritto d'autore in UK (Mishcon.com, Davide Fasoli)02:27 - Un nuovo buco nero gigante scoperto dal James Webb (Inaf.it, Luca Martinelli)03:50 - La costellazione europea per le telecomunicazioni (DDay.it, Matteo Gallo)05:15 - Gli algoritmi che ci conoscono meglio di quanto pensiamo (Luca Martinelli)16:21 - Conclusione--Contatti--• www.dentrolatecnologia.it• Instagram (@dentrolatecnologia)• Telegram (@dentrolatecnologia)• YouTube (@dentrolatecnologia)• redazione@dentrolatecnologia.it--Brani--• Ecstasy by Rabbit Theft• Capsized by Tollef

Radiology AI Podcasts | RSNA
Episode 48: Standardizing LLM Research in Radiology- Part 2

Radiology AI Podcasts | RSNA

Play Episode Listen Later Oct 11, 2024 36:41


Dr. Ali Tejani and Dr. Paul Yi discuss the current state of large language model (LLM) research and its applications in radiology with their guests Dr. Merel Huisman, Dr. Tugba Akinci D'Antonoli, and Dr. Christian Bluethgen.  They explore the rapid evolution of this field, including the surge in publications and the diverse use cases being explored. A New Era of Text Mining in Radiology with Privacy-Preserving LLMs. Akinci D'Antonoli and Bluethgen.  Radiology: Artificial Intelligence 2024; 6(4):e240261. The AI Generalization Gap: One Size Does Not Fit All. Huisman and Hannink. Radiology: Artificial Intelligence 2023; 5(5):e230246.

Radiology AI Podcasts | RSNA
Episode 47: Standardizing LLM Research in Radiology- Part 1

Radiology AI Podcasts | RSNA

Play Episode Listen Later Sep 13, 2024 28:00


Dr. Ali Tejani and Dr. Paul Yi discuss the current state of large language model (LLM) research and its applications in radiology with their guests Dr. Merel Huisman, Dr. Tugba Akinci D'Antonoli, and Dr. Christian Bluethgen.  They explore the rapid evolution of this field, including the surge in publications and the diverse use cases being explored. A New Era of Text Mining in Radiology with Privacy-Preserving LLMs. Akinci D'Antonoli and Bluethgen.  Radiology: Artificial Intelligence 2024; 6(4):e240261. The AI Generalization Gap: One Size Does Not Fit All. Huisman and Hannink. Radiology: Artificial Intelligence 2023; 5(5):e230246.

Data Culture Podcast
Data & Analytics und "Editorial Intelligence" in der Verlagsbranche – mit Ana Moya, Handelsblatt

Data Culture Podcast

Play Episode Listen Later Jul 1, 2024 32:30


Data & Analytics spielen eine entscheidende Rolle im Verlagswesen, insbesondere im Bereich der redaktionellen bzw. Editorial Intelligence.

New Books Network
Joanna Guldi, "The Dangerous Art of Text Mining: A Methodology for Digital History" (Cambridge UP, 2022)

New Books Network

Play Episode Listen Later May 28, 2024 67:40


The Dangerous Art of Text Mining: A Methodology for Digital History (Cambridge UP, 2022) celebrates the bold new research now possible because of text mining: the art of counting words over time. However, this book also presents a warning: without help from the humanities, data science can distort the past and lead to perilous errors. The book opens with a rogue's gallery of errors, then tours the ground-breaking analyses that have resulted from collaborations between humanists and data scientists.  Jo Guldi explores how text mining can give a glimpse of the changing history of the past - for example, how quickly Americans forgot the history of slavery. Textual data can even prove who was responsible in Congress for silencing environmentalism over recent decades. The book ends with an impassioned vision of what text mining in defence of democracy would look like, and why humanists need to be involved. Learn more about your ad choices. Visit megaphone.fm/adchoices Support our show by becoming a premium member! https://newbooksnetwork.supportingcast.fm/new-books-network

New Books in Science, Technology, and Society
Joanna Guldi, "The Dangerous Art of Text Mining: A Methodology for Digital History" (Cambridge UP, 2022)

New Books in Science, Technology, and Society

Play Episode Listen Later May 28, 2024 67:40


The Dangerous Art of Text Mining: A Methodology for Digital History (Cambridge UP, 2022) celebrates the bold new research now possible because of text mining: the art of counting words over time. However, this book also presents a warning: without help from the humanities, data science can distort the past and lead to perilous errors. The book opens with a rogue's gallery of errors, then tours the ground-breaking analyses that have resulted from collaborations between humanists and data scientists.  Jo Guldi explores how text mining can give a glimpse of the changing history of the past - for example, how quickly Americans forgot the history of slavery. Textual data can even prove who was responsible in Congress for silencing environmentalism over recent decades. The book ends with an impassioned vision of what text mining in defence of democracy would look like, and why humanists need to be involved. Learn more about your ad choices. Visit megaphone.fm/adchoices Support our show by becoming a premium member! https://newbooksnetwork.supportingcast.fm/science-technology-and-society

New Books in Technology
Joanna Guldi, "The Dangerous Art of Text Mining: A Methodology for Digital History" (Cambridge UP, 2022)

New Books in Technology

Play Episode Listen Later May 28, 2024 67:40


The Dangerous Art of Text Mining: A Methodology for Digital History (Cambridge UP, 2022) celebrates the bold new research now possible because of text mining: the art of counting words over time. However, this book also presents a warning: without help from the humanities, data science can distort the past and lead to perilous errors. The book opens with a rogue's gallery of errors, then tours the ground-breaking analyses that have resulted from collaborations between humanists and data scientists.  Jo Guldi explores how text mining can give a glimpse of the changing history of the past - for example, how quickly Americans forgot the history of slavery. Textual data can even prove who was responsible in Congress for silencing environmentalism over recent decades. The book ends with an impassioned vision of what text mining in defence of democracy would look like, and why humanists need to be involved. Learn more about your ad choices. Visit megaphone.fm/adchoices Support our show by becoming a premium member! https://newbooksnetwork.supportingcast.fm/technology

Exchanges: A Cambridge UP Podcast
Joanna Guldi, "The Dangerous Art of Text Mining: A Methodology for Digital History" (Cambridge UP, 2022)

Exchanges: A Cambridge UP Podcast

Play Episode Listen Later May 28, 2024 67:40


The Dangerous Art of Text Mining: A Methodology for Digital History (Cambridge UP, 2022) celebrates the bold new research now possible because of text mining: the art of counting words over time. However, this book also presents a warning: without help from the humanities, data science can distort the past and lead to perilous errors. The book opens with a rogue's gallery of errors, then tours the ground-breaking analyses that have resulted from collaborations between humanists and data scientists.  Jo Guldi explores how text mining can give a glimpse of the changing history of the past - for example, how quickly Americans forgot the history of slavery. Textual data can even prove who was responsible in Congress for silencing environmentalism over recent decades. The book ends with an impassioned vision of what text mining in defence of democracy would look like, and why humanists need to be involved.

New Work in Digital Humanities
Joanna Guldi, "The Dangerous Art of Text Mining: A Methodology for Digital History" (Cambridge UP, 2022)

New Work in Digital Humanities

Play Episode Listen Later May 28, 2024 67:40


The Dangerous Art of Text Mining: A Methodology for Digital History (Cambridge UP, 2022) celebrates the bold new research now possible because of text mining: the art of counting words over time. However, this book also presents a warning: without help from the humanities, data science can distort the past and lead to perilous errors. The book opens with a rogue's gallery of errors, then tours the ground-breaking analyses that have resulted from collaborations between humanists and data scientists.  Jo Guldi explores how text mining can give a glimpse of the changing history of the past - for example, how quickly Americans forgot the history of slavery. Textual data can even prove who was responsible in Congress for silencing environmentalism over recent decades. The book ends with an impassioned vision of what text mining in defence of democracy would look like, and why humanists need to be involved. Learn more about your ad choices. Visit megaphone.fm/adchoices Support our show by becoming a premium member! https://newbooksnetwork.supportingcast.fm/digital-humanities

KI heute
KI im Unternehmen – Zwischen Belegschaftsinitiative und CIO-Strategie

KI heute

Play Episode Listen Later Mar 12, 2024 75:15


Künstliche Intelligenz erlebt in der Unternehmenswelt einen beispiellosen Aufschwung. Aktuelle Zahlen des statistischen Bundesamts enthüllen, dass bereits jedes achte Unternehmen auf den KI-Zug aufgesprungen ist. Bei den Großunternehmen setzt sogar jedes dritte auf diese fortschrittliche Technologie. Besonders im Rampenlicht: die Anwendung von KI in der natürlichen Sprachverarbeitung. Eine beeindruckende Mehrheit von 43 % nutzt KI-Tools für die Spracherkennung, während sich 30 % auf die Analyse von Schriftsprache und Text Mining spezialisieren. Doch trotz dieser beeindruckenden Zahlen zögern noch 90 % der KI-Abstinenzler, diese Technologien einzuführen. Was genau sind die Gründe für die Nutzung? Und was hindert Unternehmen am Einsatz von Künstlicher Intelligenz?Eine Diskussion mit Dr. Ayelt Komus, Professor für Organisation und Wirtschaftsinformatik an der Hochschule Koblenz,  über seine durchgeführte Studie.Die Studie und den "Sag mal...?"-Podcast von Prof. Dr. Ayelt Komus findet ihr auf: https://www.komus.de/Fundstücke der Woche:Wie Unternehmen künstliche Intelligenz (KI) im Jahr 2024 nutzenIDC Studie - The Business Opportunity of AIOPITZ CONSULTING ■■■ Digitale Service ManufakturDisclaimer: This post contains affiliate links. If you make a purchase, I may receive a commission at no extra cost to you.Nina & Frank laden sich Gäste ein und sprechen mit ihnen über aktuelle Entwicklungen im Umfeld der Künstlichen Intelligenz.

Hidden in Plain Sight: All Things Asian in the Workplace
Business Report Deep Dive: Reading between the lines of the written and unwritten

Hidden in Plain Sight: All Things Asian in the Workplace

Play Episode Listen Later Feb 20, 2024 32:25


In this episode, we breakdown a white paper written about feedback and how it pertains to Asian professionals. What did the paper reveal about the type of feedback Asians receive from their managers, and how should we interpret these findings? Should we be skeptical? We discuss these questions and share how to be a savvy consumer of these types of business reports!

ITSPmagazine | Technology. Cybersecurity. Society
How Artificial Intelligence is revolutionizing search engines, shaping our access to information and paving the way for a more knowledgeable society | A Conversation with Consensus Co-founder, Eric Olson | Redefining Society Podcast with Marco Ciappelli

ITSPmagazine | Technology. Cybersecurity. Society

Play Episode Listen Later Jul 21, 2023 36:40


Guest: Eric Olson, Co-Founder & CEO at Consensus.app [@ConsensusNLP]On LinkedIn | https://www.linkedin.com/in/eric-olson-1822a7a6/On Twitter | https://twitter.com/IPlayedD1_____________________________Host: Marco Ciappelli, Co-Founder at ITSPmagazine [@ITSPmagazine] and Host of Redefining Society PodcastOn ITSPmagazine | https://www.itspmagazine.com/itspmagazine-podcast-radio-hosts/marco-ciappelli_____________________________This Episode's SponsorsBlackCloak

Matrix Podcast
Jo Guldi: Towards a Practice of Text Mining to Understand Change Over Historical Time

Matrix Podcast

Play Episode Listen Later Apr 15, 2023 99:33


Recorded on March 8, 2023, this video features a lecture by Jo Guldi, Professor of History and Practicing Data Scientist at Southern Methodist University. Professor Guldi's lecture was entitled “Towards a Practice of Text-Mining to Understand Change Over Historical Time: The Persistence of Memory in British Parliamentary Debates in the Nineteenth Century.” Co-sponsored by Social Science Matrix, the UC Berkeley Department of History, and D-Lab, this talk was presented as part of the Social Science / Data Science event series, a collaboration between Social Science Matrix and D-Lab. Abstract A world awash in text requires interpretive tools that traditional quantitative science cannot provide. Text mining is dangerous because analysts trained in quantification often lack a sense of what could go wrong when archives are biased or incomplete. Professor Guldi's talk reviewed a brief catalogue of disasters created by data science experts who voyage into humanistic study. It finds a solution in “hybrid knowledge,” or the application of historical methods to algorithm and analysis. Case studies engage recent work from the philosophy of history (including Koselleck, Erle, Assman, Tanaka, Chakrabarty, Jay, Sewell, and others) and investigate the “fit” of algorithms with each historical frame of reference on the past. This talk profiles recent research into the status of “memory” in British politics. It profiled the persistence of references to previous eras in British history, to historical conditions per se, and to futures hoped for and planned, using NLP analysis. It presented the promise and limits of text-mining strategies such as Named Entity Recognition and Parts of Speech Analysis for modeling temporal experience as a whole, suggesting how these methods might support students of social science and the humanities, and also revealing how traditional topics in these subjects offer a new research frontier for students of data science and informatics. About the Speaker Jo Guldi, Professor of History and Practicing Data Scientist at Southern Methodist University, is author of four books: Roads to Power: Britain Invents the Infrastructure State (Harvard 2012), The History Manifesto (Cambridge 2014), The Long Land War: The Global Struggle for Occupancy Rights (Yale 2022), and The Dangerous Art of Text Mining (Cambridge forthcoming). Her historical work ranges from archival studies in nation-building, state formation, and the use of technology by experts. She has also been a pioneer in the field of text mining for historical research, where statistical and machine-learning approaches are hybridized with historical modes of inquiry to produce new knowledge. Her publications on digital methods include “The Distinctiveness of Different Eras,” American Historical Review (August 2022) and “The Official Mind's View of Empire, in Miniature: Quantifying World Geography in Hansard's Parliamentary Debates,” Journal of World History 32, no. 2 (June 2021): 345–70. She is a former junior fellow at the Harvard Society of Fellows.

Science (Video)
The Data Science Librarian: Steward of Information

Science (Video)

Play Episode Listen Later Jun 27, 2022 17:27


Data is everywhere but how can it be effectively harnessed to answer questions and guide meaningful research? Cue the data science librarian! With a skill set that includes sourcing and vetting data as well as the ethical implications, the librarian is a key resource to researchers and students alike. UC San Diego's Stephanie Labou shares what it is like to be one of the first data science librarians and how data is changing our world. Series: "Data Science Channel" [Science] [Show ID: 37196]

University of California Audio Podcasts (Audio)
The Data Science Librarian: Steward of Information

University of California Audio Podcasts (Audio)

Play Episode Listen Later Jun 27, 2022 17:27


Data is everywhere but how can it be effectively harnessed to answer questions and guide meaningful research? Cue the data science librarian! With a skill set that includes sourcing and vetting data as well as the ethical implications, the librarian is a key resource to researchers and students alike. UC San Diego's Stephanie Labou shares what it is like to be one of the first data science librarians and how data is changing our world. Series: "Data Science Channel" [Science] [Show ID: 37196]

Science (Audio)
The Data Science Librarian: Steward of Information

Science (Audio)

Play Episode Listen Later Jun 27, 2022 17:27


Data is everywhere but how can it be effectively harnessed to answer questions and guide meaningful research? Cue the data science librarian! With a skill set that includes sourcing and vetting data as well as the ethical implications, the librarian is a key resource to researchers and students alike. UC San Diego's Stephanie Labou shares what it is like to be one of the first data science librarians and how data is changing our world. Series: "Data Science Channel" [Science] [Show ID: 37196]

UC San Diego (Audio)
The Data Science Librarian: Steward of Information

UC San Diego (Audio)

Play Episode Listen Later Jun 27, 2022 17:27


Data is everywhere but how can it be effectively harnessed to answer questions and guide meaningful research? Cue the data science librarian! With a skill set that includes sourcing and vetting data as well as the ethical implications, the librarian is a key resource to researchers and students alike. UC San Diego's Stephanie Labou shares what it is like to be one of the first data science librarians and how data is changing our world. Series: "Data Science Channel" [Science] [Show ID: 37196]

The Audit Room
Ep 4: Text Mining in Audit ft. Stephen Vigil

The Audit Room

Play Episode Listen Later Jun 8, 2022 29:12


Previously recorded in The Audit Room on Zoom co-hosted with Tracie Marquardt and Trent Russell. Join Tracie and Trent live every Tuesday to listen in or ask your questions. This podcast is brought to you by Greenskies Analytics, the services firm that helps auditors leap-frog up the analytics maturity model. Their approach for launching audit analytics programs with a series of proven quick-win analytics will guarantee the results worthy of the analytics hype. * Whether your audit team needs a data strategy, methodology, governance, literacy, or anything else related to audit and analytics, schedule time with Greenskies Analytics. This podcast is also brought to you by Quality Assurance Communication If you are an internal auditor who wants to take your own, or your team's, communication skills and audit results to the next level, who wants to create more for yourself, your team and your organization - no matter where you work around the globe - then check out Quality Assurance Communication, at qacommunication.com.

Teknologi og data podcast
Hvad Er Text Mining?

Teknologi og data podcast

Play Episode Listen Later May 31, 2022 1:36


Hvad Er Text Mining? by Viden om data

The Academic Minute
Charlotte Alexander, Georgia State University – Text Mining for Bias: A Recommendation Letter Experiment

The Academic Minute

Play Episode Listen Later Aug 26, 2021 2:30


How do we hire a more diverse workforce? Charlotte Alexander, associate professor of legal analytics at Georgia State University, details how to avoid bias when looking for new employees. Charlotte S. Alexander is an associate professor of legal analytics at Georgia State University's Robinson College of Business and director of its Legal Analytics Lab, which is a joint initiative […]

Building The Future - AI Portugal Podcast

Hoje o tópico deste episodio é Text Mining, o processo de extrair meta-informação de texto, isto é uma área do Data Mining que temos visto crescer imenso nos últimos anos, com múltiplas aplicações desde Categorização, clustering, Extração de Entidades, analise de sentimento, sumarização , entre outras… Hoje vamos falar um pouco sobre estas técnicas, o que são, para que servem, que impacto tem tido nas nossas vidas e na transformação digital Um episódio que não vais querer perder! AI News: 7 AI-Based Movies To Look Forward To In 2021 https://analyticsindiamag.com/7-ai-based-movies-to-look-forward-to-in-2021/ http://lxmls.it.pt/2021/ This Researcher Says AI Is Neither Artificial nor Intelligent | WIRED https://www.wired.com/story/researcher-says-ai-not-artificial-intelligent/ Hosts: Marco António Silva: https://www.linkedin.com/in/marconsilva/ José António Silva: https://www.linkedin.com/in/canoas/ Vitor Santos: https://www.linkedin.com/in/vitor-santos-ab87662/

Strefa Psyche Uniwersytetu SWPS
Uczenie maszynowe w wykrywaniu schizofrenii - dr Justyna Sarzyńska, dr inż. Aleksander Wawer

Strefa Psyche Uniwersytetu SWPS

Play Episode Listen Later Feb 24, 2021 63:56


Czy komputery są w stanie rozpoznawać schizofrenie równie skutecznie jak psychiatrzy? Czy stan pacjenta można monitorować na odległość? Wraz z rozwojem metod NLP (przetwarzania języka naturalnego) i uczenia maszynowego przybywa obiektywnych narzędzi przydatnych w diagnostyce i monitorowaniu stanu pacjentów cierpiących na różne choroby i zaburzenia psychiczne. Podczas wykładu omówimy modele głębokiego uczenia maszynowego wykorzystywane w wykrywaniu formalnych zaburzeń myślenia (jednego z głównych objawów schizofrenii) na podstawie tekstu. Opowiemy o naszych badaniach, w których porównywaliśmy skuteczność metod komputerowych z ocenami psychiatry. Poruszymy również problematykę przyszłości metod komputerowych w psychiatrii. dr Justyna Sarzyńska-Wawer – adiunkt w Pracowni Psycholingwistyki i Psychologii Poznawczej w Instytucie Psychologii PAN. Kierownik i wykonawca w grantach dotyczących podstawowych procesów poznawczych oraz neuronalnych i poznawczych korelatów kłamania. Obecnie prowadzi badania nad wykrywaniem kłamania poprzez automatyczną analizę tekstu i użyciem metod uczenia maszynowego w diagnozowaniu chorób psychicznych. Pracę naukową łączy z terapeutyczną (w nurcie poznawczo-behawioralnym). dr inż. Aleksander Wawer – adiunkt w Zespole Inżynierii Lingwistycznej w Instytucie Podstaw Informatyki PAN. Pracuje również w laboratorium Text Mining w Samsung R&D Poland, gdzie zajmuje się praktycznymi implementacjami technologii językowych. Jego zainteresowania i wieloletnie doświadczenie zawodowe obejmują przetwarzanie języka naturalnego (NLP), zarówno składniowe, jak i semantyczne. Jest zafascynowany głębokim uczeniem maszynowym i wielowarstwowymi sieciami neuronowymi oraz ich zastosowaniami w analizie wydźwięku (sentiment analysis), wykrywaniu fake newsów oraz w szeroko pojętej psychologii i psychiatrii. Wykład odbył się w ramach kolejnej edycji Dnia Mózgu 2020 na Uniwersytecie SWPS w Warszawie. Więcej o wydarzeniu: https://www.swps.pl/uczelnia/aktualnosci/21277-dzien-mozgu-2020

SoLeadSaturday
SoLeadSaturday - Episode 56 - Koo Ping Shung #ai #datasciene #innovation #mentor

SoLeadSaturday

Play Episode Listen Later Dec 26, 2020 24:51


Hello Everyone, The guest we have today, Koo Ping Shung is a Data scientist armed with an MBA degree & 15 years of relevant experience. A strong & passionate advocate of Data Science & Artificial Intelligence who Artificial Intelligence that can be used to better humanity. His advocacy work in the day is by helping businesses to build internal data capabilities, at night building tech communities through DataScience SG and AI Professionals Association. Ping Shung is experienced in the full process of getting value from data, from data collection, management & governance to implementation of insights through strategy and business performance measurement. Experienced in Data Governance & Management, Data Visualization, Machine Learning, and Text Mining. He shared this knowledge through training, mentoring, and consulting. To date, he has clocked at least 2000 man-hours of training. His research interest is in how an organization can build Data Science & Artificial Intelligence capabilities to derive value from their data and how to build Artificial General Intelligence. Quick Summary: Passion & Interest [2:10 - 5:07] Questions from Audience [5:07 - 11:11] Fun Segment [11:11 - 11:53] Career/Work/Volunteering [11:53 - 17:51] Tips/Advice/Books [17:51 - 20:50] Leadership [20:50 - 23:51] Closure & Thank you [23:51 - end] So watch the complete episode: https://youtu.be/LZ-F3ouXl6U Listen to the complete episode: https://anchor.fm/vaishali-lambe/episodes/SoLeadSaturday---Episode-56---Koo-Ping-Shung-ai-datasciene-innovation-mentor-eo8bth If you would like to connect with him please feel free to do so @LinkedIn Until we meet, happy leading and let's lead together. Stay safe. Bye for now. Find me on - Twitter - https://twitter.com/vaishalilambe LinkedIn - https://www.linkedin.com/in/vaishali-lambe/ Instagram - @PassionPeoplePurpose Website - https://www.vaishalilambe.com/soleadsaturday Facebook - https://www.facebook.com/vaishalilambe17 Apple Podcasts - https://podcasts.apple.com/us/podcast/soleadsaturday/id1496626534?uo=4 Google Podcasts - https://www.google.com/podcasts?feed=aHR0cHM6Ly9hbmNob3IuZm0vcy8xMzFiYTA0MC9wb2RjYXN0L3Jzcw== Spotify - https://open.spotify.com/show/0bFOIm9EGFalhPG8YPBhVp --- Support this podcast: https://anchor.fm/vaishali-lambe/support

PaperPlayer biorxiv bioinformatics
emiRIT: A text-mining based resource for microRNA information

PaperPlayer biorxiv bioinformatics

Play Episode Listen Later Nov 6, 2020


Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.11.05.370593v1?rss=1 Authors: Roychowdhury, D., Gupta, S., Qin, X., Arighi, C. N., Vijay-Shanker, K. Abstract: Motivation: microRNAs (miRNAs) are essential gene regulators and their dysregulation often leads to diseases. Easy access to miRNA information is crucial for interpreting generated experimental data, connecting facts across publications, and developing new hypotheses built on previous knowledge. Here, we present emiRIT, a text mining-based resource, which presents miRNA information mined from the literature through a user-friendly interface. Results: We collected 149,233 miRNA-PubMed ID pairs from Medline between January 1997 to May 2020. emiRIT currently contains miRNA-gene regulation (60,491 relations); miRNA-disease (cancer) (12,300 relations); miRNA-biological process and pathways (23,390 relations); and circulatory miRNAs in extracellular locations (3,782 relations). Biological entities and their relation to miRNAs were extracted from Medline abstracts using publicly available and in-house developed text mining tools, and the entities were normalized to facilitate querying and integration. We built a database and an interface to store and access the integrated data, respectively. Conclusion: We provide an up-to-date and user-friendly resource to facilitate access to comprehensive miRNA information from the literature on a large-scale, enabling users to navigate through different roles of miRNA and examine them in a context specific to their information needs. To assess our resource's information coverage, in the absence of gold standards, we have conducted two case studies focusing on the target and differential expression information of miRNAs in the context of diseases. Database URL: https://research.bioinformatics.udel.edu/emirit/ Copy rights belong to original authors. Visit the link for more info

Data Leadership Lessons Podcast
Building Analytics Teams with Keith McCormick - Episode 22

Data Leadership Lessons Podcast

Play Episode Listen Later Sep 28, 2020 40:52


Watch this episode on YouTube: https://youtu.be/RnGRqHmVQ2M * Get the Data Leadership Book – https://dataleadershipbook.com * Data Leadership Lessons on YouTube – https://www.youtube.com/c/DataLeadershipLessons* Save 20% on your first order at the DATAVERSITY Training Center with promo code “AlgminDL” – https://training.dataversity.net/?utm_source=algmindl_res * Guest and Sponsorship Inquiries – podcast@algmin.com This week we welcome Keith McCormick. Keith has a wealth of consulting experience in statistics, predictive analytics, and data mining. For many years, he has worked in the SPSS community, first as an External Trainer and Consultant for SPSS Inc., and then in a similar role with IBM. He possesses a BS in Computer Science and Psychology from Worcester Polytechnic Institute. A sought after speaker, he routinely leads workshops at the popular TDWI conferences, and has given keynotes presentations at many international events. He is an expert in IBM’s SPSS software suite including IBM SPSS Statistics, IBM SPSS Modeler, AMOS, and Text Mining. He is active in statistics groups online and blogs at KeithMcCormick.com. He has twelve courses on LinkedIn Learning, and has coauthored 6 books, including SPSS Statistics For Dummies, 4th edition (August 2020), and Effective Data Preparation (Cambridge University Press, Fall 2020). He is an award winning instructor for UC Irvine’s Predictive Analytics certificate program, and serves on the program’s advisory board. Since serving as a VP of analytics for a small consultancy, his consulting has shifted emphasis towards helping his clients build and manage their analytics teams. For more information about our guest:– Keith McCormick on LinkedIn: https://www.linkedin.com/in/keithmccormick/– Home Page: https://KeithMcCormick.com– Book: SPSS Statistics For Dummies: https://www.amazon.com/dp/1118989015

Datenbusiness Podcast
#39 Datenchefs #30 mit Dr. Gerhard Rolletschek | Co-Founder & MD Glanos | Text-Analytics & Business-Monitoring

Datenbusiness Podcast

Play Episode Listen Later Sep 20, 2020 65:43


Dr. Gerhard Rolletschek ist einer der beiden Gründer der Glanos GmbH und Experte auf dem Gebiet der semantischen Datamining-Technologie mit einem speziellen Fokus auf Firmendatenextraktion und –aggregation. Er ist promovierter Computerlinguist und hat seit 2003 zahlreiche Projekte mit renommierten internationalen Kunden im Bereich Informationsextraktion und Suchtechnologien durchgeführt. Die wichtigsten Themen im Überblick: Zu den Ursprüngen von Hyperlinks und Hypertext. (ab 02:43) Was macht Glanos? (ab 07:26) Das Problem der Re-Identifikation. (ab 10:03) Mitbewerberanalyse mittels Text-Mining. (ab 16:20) Wieviel Linguistik steckt noch in heutigen Text-Analytics-Lösungen? (ab 21:52) Mitbewerberanalyse als konkretes Beispiel. (ab 25:33) Klassifikation von Stellenanzeigen als weiteres konkretes Beispiel. (ab 32:05) Fake News erkennen. (ab 38:46) Herausforderungen mit Social Media. (ab 46:28) Einschätzung zu GPT-3. (ab 54:34)

PaperPlayer biorxiv bioinformatics
Komenti: A semantic text mining framework

PaperPlayer biorxiv bioinformatics

Play Episode Listen Later Aug 4, 2020


Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.08.04.233049v1?rss=1 Authors: Slater, L. T., Bradlow, W., Hoehndorf, R., Motti, D. F., Ball, S., Gkoutos, G. V. Abstract: Komenti is a reasoner-enabled semantic query and information extraction tool. It is the only text mining tool that enables querying inferred knowledge from biomedical ontologies. It also contains multiple novel components for vocabulary construction and context disambiguation, which can improve the power of text mining and ontology-based analysis tasks, with a view towards making full use of the semantic provision of biomedical ontologies in the text extraction and characterisation space. Here, we describe Komenti, its features, and a use case wherein we automate a clinical audit process, classifying the medications of patients with hypertrophic cardiomyopathy from text records, revealing a high precision, and a subcohort of candidate patients who have atrial fibrillation but were not anti-coagulated, and are therefore at a higher risk of stroke. Copy rights belong to original authors. Visit the link for more info

Marketing Over Coffee Marketing Podcast
Geekery, and Marketing AI Tactics 1 of 5

Marketing Over Coffee Marketing Podcast

Play Episode Listen Later Jul 31, 2020


In this Marketing Over Coffee: Learn about AI for Transcription and Data Mining, GPT3, Weav Run, and more! Direct Link to File Brought to you by our sponsors: Direct Mail and LinkedIn. Smart Studio Light AI Project #1 – Text Mining and Natural Language Processing – scanning millions of chats per day 7:14 – 8:41 […] The post Geekery, and Marketing AI Tactics 1 of 5 appeared first on Marketing Over Coffee Marketing Podcast.

Develomentor
Dr. Ryan Rosario - How to Excel at Statistics and Computer Science? #78

Develomentor

Play Episode Listen Later Jul 30, 2020 35:48


Welcome to another episode of Develomentor. Today's guest is Dr. Ryan Rosario!Dr. Ryan Rosario is currently a Data Scientist at Google, in the Search area, and Lecturer for the UCLA Department of Computer Science. Prior to Google, Ryan has worked at both Facebook and Amazon. Ryan has split his time between industry and academia. His research, academic and work interests include Machine Learning, Text Mining and Natural Language Processing. If you are enjoying our content please leave us a rating and review or consider supporting usQuotes“It wasn’t until I was in the middle of my undergraduate career when I realized how much computer science and statistics went together.”“For me, security is most important. Although I’ve worked at startups and really enjoyed them, I personally like the bigger company culture better.”“99 percent of the time as a data scientist is spent with data management. I actually enjoy this! It should actually be a passion for people to enjoy data management.”“You have to find your own projects on your own using data that’s in your interest area. If you’re interested in the problem being solved you’ll be able to develop the intuition to solve the problem.”—Ryan RosarioKey MilestonesMany of our listeners are often wonder about pursuing graduate studies after college. Ryan did two master’s and a PhD. What inspired him to go so deep?Ryan has managed to keep one foot in both academia and industry. How has he been able to organize this kind of balance?Ryan got dual master’s degrees in statistics and computer science. What is a quantitative engineer?Ryan explains how to develop data intuition. Text and natural language processingWhat are some key skills that will help you be successful in data science?Additional ResourcesGuide to learning R for data science – https://www.dataquest.io/blog/learn-r-for-data-science/Check out Ryan’s blog – http://www.bytemining.com/You can find more resources in the show notesTo learn more about our podcast go to https://develomentor.com/To listen to previous episodes go to https://develomentor.com/blog/Connect with Dr. Ryan RosarioLinkedInTwitterBlogFollow DevelomentorTwitter: @develomentorConnect with Grant IngersollLinkedInTwitter

Efekt Sieci
#23 Badanie pandemii metodą text mining

Efekt Sieci

Play Episode Listen Later Jul 8, 2020 19:45


Gośćmi dr Justyny Pokojskiej (DELab UW | IS UW) są Krisfóf Gyódi (DELab UW | WNE UW) i Michał Paliński (DELab UW | WNE UW), którzy odpowiadają o badaniu pandemii COVID-19 metodą text mining: ➡️ Czym jest infodemia i jak ją badać? ➡️ Na czym polega text minining i co jest fascynującego w tej metodzie? ➡️ Na po powinno zwracać się uwagę w badaniach nad tekstem? ➡️ Co wyszło z badań pandemii? Co można na ich podstawie powiedzieć o naszym (społeczeństwa) stanie wiedzy w dobie COVID-19? Jak fluktuowało nasze zainteresowanie - co było na topie i jak to się zmieniało? ➡️ Czy uczenie się data science na zbiorach danych o zgonach jest etyczne? ➡️ Czy doświadczamy obecnie zalewu prac naukowych o wątpliwej jakości?

Captivated Audience: A Financial Crime Podcast
AML Technology: Detection, Investigation and Analytics - Christopher Ghenne, Global Lead - Banking Compliance Solutions - SAS (Brussels, recorded on 19 May 2020)

Captivated Audience: A Financial Crime Podcast

Play Episode Listen Later May 27, 2020 14:50


Christopher Ghenne, Global Lead - Banking Compliance Solutions - SAS joins Marie Lundberg and Sam Sheen to chat about how he supervises 600 team members across 50+ countries over the restricted period, the evolution of the SAS transaction monitoring tool and its use of big data, the use of advanced analytics and text mining and analysis of unstructured data for sanctions screening. They also discuss the challenges of sanctions screening and the dance between transaction monitoring and name screening and why text mining makes it move more smoothly across the compliance dance floor. If you have ever wondered how to set up an effective monitoring tool, this is the podcast to listen to!

The Medical Republic
Computers can't read your clinical notes

The Medical Republic

Play Episode Listen Later Feb 24, 2020 26:49


Human language is hard for AI to wrap its circuit boards around at the best of times. But the typos, abbreviations, spelling mistakes, redundancy and messy structure of clinical notes makes it the worst-case scenario for text mining. Lots of research teams are trying to solve this problem – but it's proving much more difficult than anyone expected.

Digital Trasformation
Modelli supervisionati e non supervisionati per il Data Mining

Digital Trasformation

Play Episode Listen Later Jan 22, 2020 3:53


Esistono due categorie di metodi per poter effettuare il processo di Data Mining, e cioè di estrazione dei dati.I modelli “supervisionati”, che sono metodi che vengono applicati nel momento in cui nel data set di partenza esiste una variabile di raggruppamento, o etichetta, e i modelli “non supervisionati” che non hanno questa variabile di raggruppamento.I supervisionati si dividono in altre due sottocategorie di metodi di estrazione e sono di “Classificazione” o di “Regressione” in base alla variabile di raggruppamento se di tipo cardinale o numerico quantitativo. Nei metodi non supervisionati, quando non esiste la variabile di raggruppamento, abbiamo modelli di Clustering o modelli di Regole di associazione.La fase preliminare di estrazione dei dati è il momento più critico in quanto è caratterizzata dalla preparazione del dato che passa da alcuni step prevalenti; l’acquisizione del dato, la fase di Parsing, quindi di conversione dei dati in una unica struttura e formato, la fase di controllo, che deve prendere in considerazione i casi mancanti e le anomalie.Tra i modelli supervisionati di classificazione esiste il metodo KNN, o del vicino più prossimo, che si basa sulle caratteristiche vicine al dato considerato. Un oggetto è classificato in base alla maggioranza dei voti dei suoi vicini.Il metodo degli alberi di classificazione, o decisione, che rappresenta un albero di classificatori con nodi interni binari, chiamati foglie, che dividono i campioni in classi di etichette omogenee, stratificando i dati.I modelli supervisionati di regressione possono essere lineari, quindi una stima basata su una variabile dipendente e una o più variabili indipendenti, e a vettori di supporto, (Support Vector Machine) che costruisce nuovi esempi ad una delle classi possibili ottenendo un classificatore binario non probabilistico.I principali ambiti di applicazione possono essere per classificare i comportamenti di acquisto, per una diagnosi medica, per la sicurezza web o per il rilevamento dello spam.Invece i modelli non supervisionati, quindi senza variabile di raggruppamento, vengono utilizzati per la sentiment analysis, per analizzare l’e-commerce o per valutare i dati in store.L’esempio più calzante è il modello basket analysis che permette di analizzare le abitudini di acquisto dei clienti identificando le relazioni esistenti tra prodotti acquistati e differenti consumatori.Anche il Clustering figura tra i metodi non supervisionati, e consiste nel raggruppare dati omogenei basandosi sulla somiglianza, e quindi la distanza tra di loro, in uno spazio multidimensionale. In ultimo ci sono metodi di text mining che si applicano a testi non strutturati, estraendo informazioni a valore aggiunto convertendoli in linguaggio strutturato e formale.Si utilizzano per pagine web, email, social, agenzie stampa, chat ecc..in questi casi i campi di applicazione sono la brand reputation, la sentiment analysis, la seo e il web marketing.

Neofonie Blogcast
Text Mining und NLP-Frameworks im Vergleich

Neofonie Blogcast

Play Episode Listen Later Sep 4, 2019 6:16


Das KI-Team der Neofonie hat NLP-Framworks, die auch deutsche Textdaten verarbeiten, untersucht und getestet. Die Ergebnisse, die bei der Suche nach dem passenden NLP-Framework helfen, stellt Cornelia Werk im Blogbeitrag vor.

De Dataloog
DTL Big Data Expo Special – Text Mining in de zorg sector

De Dataloog

Play Episode Listen Later Jul 26, 2019 42:45


Op aanvraag van Big Data Expo (BDE) nemen we deze periode enkele Dataloog uitzendingen op die specifiek gaan over onderwerpen die tijdens BDE aan bod komen. In deze uitzending staat Text Mining centraal. Naast analyse van discrete vormen van data (sensor data, invulvelden) is het ook zinvol om op vrije invulvelden analyses uit te doen.  De Dataloog spreekt met Ivo Everts en Ruth Stoffels over Text Mining op basis van elektronisch patienten dossier. We praten over de geschiedenis en staat van text mining in het Nederlands, het ImageNet moment, en uiteraart over BERT en BAAS. Daarbij lichten we een mooie case uit over de potentie van het gebruiken van vrije invulvelden in het EPD (ingevuld door arten en verpleegkundigen ) voor het voorspellen van onverwachte herhaalde ziekenhuisbezoeken.

Edureka: Trending Technologies
Natural Language Processing Explained

Edureka: Trending Technologies

Play Episode Listen Later Jun 21, 2019 7:24


This Episode will provide you with a short and crisp description of NLP (Natural Language Processing) and Text Mining. You will also learn about the various applications of NLP in the industry. #NLPin10minutes #NLPtutorial #NLPtraining #Edureka

DataBytes
#20: Thinking Like Computers and Text Mining the Mueller Report

DataBytes

Play Episode Listen Later Apr 26, 2019 21:44


In this episode, we discuss a study that recruits human researchers to try to predict how computers classify images. We then highlight a number of examples of natural language processing techniques applied to the Mueller Report. --- Send in a voice message: https://anchor.fm/databytes/message Support this podcast: https://anchor.fm/databytes/support

Gresham College Lectures
Text Mining: How Do Computers Understand Language?

Gresham College Lectures

Play Episode Listen Later Apr 16, 2019 51:56


Text is everywhere. From tweets to the gigantic records of governments, machine processing of text is now subtle and pervasive. We can automatically identify authors of works, look for disease within tweets and even construct chatbots which can convince some people that these machines are human. In this lecture, we provide a brief history of text processing and look towards the future when the computer sonnet or love poem might become a reality.A lecture by Richard Harvey, IT Livery Company Professor of Information Technology 16 April 2019The transcript and downloadable versions of the lecture are available from the Gresham College website: https://www.gresham.ac.uk/lectures-and-events/text-miningGresham College has been giving free public lectures since 1597. This tradition continues today with all of our five or so public lectures a week being made available for free download from our website. There are currently over 2,000 lectures free to access or download from the website.Website: http://www.gresham.ac.uk Twitter: http://twitter.com/GreshamCollege Facebook: https://www.facebook.com/greshamcollege Instagram: http://www.instagram.com/greshamcollege

Data Skeptic
Text Mining in R

Data Skeptic

Play Episode Listen Later Feb 22, 2019 20:28


Kyle interviews Julia Silge about her path into data science, her book Text Mining with R, and some of the ways in which she's used natural language processing in projects both personal and professional. Related Links https://stack-survey-2018.glitch.me/ https://stackoverflow.blog/2017/03/28/realistic-developer-fiction/

Stats + Stories
Analyzing Art Through Text Mining | Stats + Stories Episode 79

Stats + Stories

Play Episode Listen Later Jan 17, 2019 28:40


Julia Silge is a data scientist at Stack Overflow, with a PhD in astrophysics and an abiding love for Jane Austen. She is both an international speaker and a real-world practitioner focusing on data analysis and machine learning practice. She is the author of Text Mining with R, with her coauthor David Robinson. She loves making beautiful charts and communicating about technical topics with diverse audiences.

Women in AI
Episode 76: Text Mining Techniques: FINRA & Fraud Detection

Women in AI

Play Episode Listen Later Oct 17, 2018 13:30


Women in AI is a biweekly podcast from RE•WORK, meeting with leading female minds in AI, Deep Learning and Machine Learning. We will speak to CEOs, CTOs, Data Scientists, Engineers, Researchers and Industry Professionals to learn about their cutting edge work and technological advancements, as well as their impact on AI for social good and diversity in the workplace.

Colper Science
Episode 14: Content Mine: scientific literature exploration through text mining

Colper Science

Play Episode Listen Later Apr 10, 2018 53:32


In this episode, we interviewed [Peter Murray Rust](https://twitter.com/thecontentmine?lang=en), chemist at Cambridge University. Peter is also known for his work and support related to open access and open data, among his projects is the [Content Mine](http://contentmine.org/) software chain about which we talked in this episode. The Content Mine group currently offer and maintain these open source software, but it also offers consulting services to assist individuals or groups interested in the suite of software. Content Mine is a suite of open source software designed to mine and analyze the scientific literature. Three packages are currently offered by the [Content Mine group](https://github.com/ContentMine): getpapers, ami and norma. These 3 packages should allow us to download large sets of papers about a certain subject, normalize the obtained data to better explore it and then start analyzing using basic tools such as word counts and regular expressions. We explored and discussed these packages and how they could serve a researcher. You will also learn about the history of ContentMine, its team and the opinion of publishers, such as Elsevier, regarding such practices. Blogpost: http://blog.colperscience.com/contentmine

Unit for Biocultural Variation and Obesity (UBVO) seminars

A presentation by John McNaught (Deputy Director of the National Centre for Text Mining) for the UBVO Obesity, eating disorders and the media workshop in November 2017

Digital History seminar
Text Mining the History of Medicine

Digital History seminar

Play Episode Listen Later Mar 23, 2015


Institute of Historical Research Text Mining the History of Medicine Sophia Ananiadou (Manchester University) I will present the results of a collaborative and interdisciplinary project between the National Centre for Text Mining (NaCTeM) and...

Digital History seminar
Text Mining the History of Medicine

Digital History seminar

Play Episode Listen Later Mar 23, 2015 57:23


Institute of Historical Research Text Mining the History of Medicine Sophia Ananiadou (Manchester University) I will present the results of a collaborative and interdisciplinary project between the National Centre for Text Mining (NaCTeM) and...

SJSU iSchool Audio/Video Podcast
Steven Ramirez: How Cutting Edge Information and Text Mining Creates Hidden Value (VIDEO)

SJSU iSchool Audio/Video Podcast

Play Episode Listen Later Aug 6, 2013 63:37


What secrets about information collection, modeling, and data analysis techniques do innovative management consultants deliver to succeed in the competitive private sector? This timely presentation demonstrates how Beyond the Arc, consultants to one of the world's largest banks, unlocks and integrates the value of commonly underutilized data sources, advanced data mining, and text analytics attract and retain profitable clients and improve customer experience.

SJSU iSchool Audio/Video Podcast
Steven Ramirez: How Cutting Edge Information and Text Mining Creates Hidden Value (AUDIO)

SJSU iSchool Audio/Video Podcast

Play Episode Listen Later Aug 6, 2013 63:37


What secrets about information collection, modeling, and data analysis techniques do innovative management consultants deliver to succeed in the competitive private sector? This timely presentation demonstrates how Beyond the Arc, consultants to one of the world's largest banks, unlocks and integrates the value of commonly underutilized data sources, advanced data mining, and text analytics attract and retain profitable clients and improve customer experience.

Columbia Ideas at Work
Oded Netzer: Text Mining Social Media for Consumer Insights

Columbia Ideas at Work

Play Episode Listen Later Jun 19, 2013 15:12


Professor Oded Netzer discusses how the emerging science of text mining is helping marketers measure their impact — and the surprising insights the field may offer the healthcare industry.

Science Selections
Text Mining Spat - Mar, 20, 2013 Nature

Science Selections

Play Episode Listen Later Mar 23, 2013 12:32


"Scientists and publishers clash over licences that would let machines read research papers." by Richard Van Noorden

Science Selections
Text Mining Spat - Mar, 20, 2013 Nature

Science Selections

Play Episode Listen Later Mar 23, 2013 12:32


"Scientists and publishers clash over licences that would let machines read research papers." by Richard Van Noorden

Business Intelligence
Business Intelligence - Geschichtlicher Abriss: Business Intelligence

Business Intelligence

Play Episode Listen Later Mar 15, 2013 4:05


Diese Animation stammt aus dem Kurs Business Intelligence im Online Wirstschaftsinformatik Fernstudiengang. Mehr Infos: http://oncampus.de/index.php?id=1205 Neben modell- und datengetriebenen Entscheidungsunterstützungssystemen werden kommunikations-, dokumenten- und Wissensbasierte Systeme unterschieden. Um abschätzen zu können, woher das Business Intelligence kommt und wo seine informationstechnischen Wurzeln liegen, soll in diesem Abschnitt ein kleiner historischer Abriss erfolgen. Bei kommunikationsgetriebenen Systemen, wie z.B. Groupware- oder Videokonferenzsysteme, steht die Unterstützung der Kommunikation und Kollaboration im Rahmen von Entscheidungsprozessen im Vordergrund. Dokumentengetriebene Systeme stellen das Retrieval von Dokumenten und die Analyse der Dokumente ins Zentrum der computergestützten Entscheidungsunterstützung. Im Gegensatz zu datengetriebenen Systemen, die in der Regel auf eher strukturierten Daten basieren, sind dokumentengetriebene Systeme auf unstrukturierte, textbasierte Daten ausgerichtet. Diese Differenzierung wird aber zunehmend unschärfer, da zunehmend auch unstrukturierte Daten z.B. im Rahmen des Text Mining in BI-Systemen verwendet werden. Unter die Bezeichnung Wissensbasierte Entscheidungsunterstützungssystem fallen Expertensysteme, die für eine in der Regel recht eingegrenzte Wissensdomäne Expertenwissen mit Methoden der künstlichen Intelligenz zur Verfügung stellen.

Keynote presentations at the 7th International Conference on Spatial data Quality (ISSDQ 2011)
Analysing land cover and green space consultation semantics: concepts, overlaps and mappings

Keynote presentations at the 7th International Conference on Spatial data Quality (ISSDQ 2011)

Play Episode Listen Later Jul 11, 2012 46:37


Analysing land cover and green space consultation semantics: concepts, overlaps and mappings

Digital Tools workshop (Histore Project)
An Introduction to Text Mining

Digital Tools workshop (Histore Project)

Play Episode Listen Later Jun 20, 2012 20:06


Institute of Historical Research 2 An Introduction to Text Mining Matteo Romanello (DAI/KCL) Matteo describes the process of text mining and how it might be useful for historians. Digital Tools workshop

STM Innovations Seminar 2011 [Video]
Text Mining meets Crowd Sourcing: author disambiguation in High-Energy Physics

STM Innovations Seminar 2011 [Video]

Play Episode Listen Later Dec 28, 2011 19:59


Digital History seminar
Text Mining the Old Bailey Proceedings

Digital History seminar

Play Episode Listen Later Jun 12, 2011 41:39


Institute of Historical Research Text Mining the Old Bailey Proceedings Professor Tim Hitchcock (Hertfordshire) The Old Bailey Online is probably one of the most successful web-based projects produced in Britain thus far. Based on the procee...

Digital History seminar
Text Mining the Old Bailey Proceedings Discussion

Digital History seminar

Play Episode Listen Later Jun 12, 2011 45:26


Institute of Historical Research Text Mining the Old Bailey Proceedings Discussion Professor Tim Hitchcock (Hertfordshire) The Old Bailey Online is probably one of the most successful web-based projects produced in Britain thus far. Based o...

E-books and E-content 2010 [Audio]
Data and text mining: the search for unknown knowns

E-books and E-content 2010 [Audio]

Play Episode Listen Later Jun 4, 2010 29:13


Economic Research
Text Mining of Electronic News Content for Economic Research, Pt. 3

Economic Research

Play Episode Listen Later Dec 4, 2009 16:53


nyu, stern, speaker, business, internet, economy, politics, shopping, guest

Economic Research
Text Mining of Electronic News Content for Economic Research, Pt. 2

Economic Research

Play Episode Listen Later Dec 4, 2009 16:53


nyu, stern, speaker, business, internet, economy, politics, shopping, guest

Economic Research
Text Mining of Electronic News Content for Economic Research, Pt. 1

Economic Research

Play Episode Listen Later Dec 4, 2009 16:53


nyu, stern, speaker, business, internet, economy, politics, shopping, guest

Fakultät für Mathematik, Informatik und Statistik - Digitale Hochschulschriften der LMU - Teil 01/02
Text Mining and Gene Expression Analysis Towards Combined Interpretation of High Throughput Data

Fakultät für Mathematik, Informatik und Statistik - Digitale Hochschulschriften der LMU - Teil 01/02

Play Episode Listen Later Sep 13, 2007


Microarrays can capture gene expression activity for thousands of genes simultaneously and thus make it possible to analyze cell physiology and disease processes on molecular level. The interpretation of microarray gene expression experiments profits from knowledge on the analyzed genes and proteins and the biochemical networks in which they play a role. The trend is towards the development of data analysis methods that integrate diverse data types. Currently, the most comprehensive biomedical knowledge source is a large repository of free text articles. Text mining makes it possible to automatically extract and use information from texts. This thesis addresses two key aspects, biomedical text mining and gene expression data analysis, with the focus on providing high-quality methods and data that contribute to the development of integrated analysis approaches. The work is structured in three parts. Each part begins by providing the relevant background, and each chapter describes the developed methods as well as applications and results. Part I deals with biomedical text mining: Chapter 2 summarizes the relevant background of text mining; it describes text mining fundamentals, important text mining tasks, applications and particularities of text mining in the biomedical domain, and evaluation issues. In Chapter 3, a method for generating high-quality gene and protein name dictionaries is described. The analysis of the generated dictionaries revealed important properties of individual nomenclatures and the used databases (Fundel and Zimmer, 2006). The dictionaries are publicly available via a Wiki, a web service, and several client applications (Szugat et al., 2005). In Chapter 4, methods for the dictionary-based recognition of gene and protein names in texts and their mapping onto unique database identifiers are described. These methods make it possible to extract information from texts and to integrate text-derived information with data from other sources. Three named entity identification systems have been set up, two of them building upon the previously existing tool ProMiner (Hanisch et al., 2003). All of them have shown very good performance in the BioCreAtIvE challenges (Fundel et al., 2005a; Hanisch et al., 2005; Fundel and Zimmer, 2007). In Chapter 5, a new method for relation extraction (Fundel et al., 2007) is presented. It was applied on the largest collection of biomedical literature abstracts, and thus a comprehensive network of human gene and protein relations has been generated. A classification approach (Küffner et al., 2006) can be used to specify relation types further; e. g., as activating, direct physical, or gene regulatory relation. Part II deals with gene expression data analysis: Gene expression data needs to be processed so that differentially expressed genes can be identified. Gene expression data processing consists of several sequential steps. Two important steps are normalization, which aims at removing systematic variances between measurements, and quantification of differential expression by p-value and fold change determination. Numerous methods exist for these tasks. Chapter 6 describes the relevant background of gene expression data analysis; it presents the biological and technical principles of microarrays and gives an overview of the most relevant data processing steps. Finally, it provides a short introduction to osteoarthritis, which is in the focus of the analyzed gene expression data sets. In Chapter 7, quality criteria for the selection of normalization methods are described, and a method for the identification of differentially expressed genes is proposed, which is appropriate for data with large intensity variances between spots representing the same gene (Fundel et al., 2005b). Furthermore, a system is described that selects an appropriate combination of feature selection method and classifier, and thus identifies genes which lead to good classification results and show consistent behavior in different sample subgroups (Davis et al., 2006). The analysis of several gene expression data sets dealing with osteoarthritis is described in Chapter 8. This chapter contains the biomedical analysis of relevant disease processes and distinct disease stages (Aigner et al., 2006a), and a comparison of various microarray platforms and osteoarthritis models. Part III deals with integrated approaches and thus provides the connection between parts I and II: Chapter 9 gives an overview of different types of integrated data analysis approaches, with a focus on approaches that integrate gene expression data with manually compiled data, large-scale networks, or text mining. In Chapter 10, a method for the identification of genes which are consistently regulated and have a coherent literature background (Küffner et al., 2005) is described. This method indicates how gene and protein name identification and gene expression data can be integrated to return clusters which contain genes that are relevant for the respective experiment together with literature information that supports interpretation. Finally, in Chapter 11 ideas on how the described methods can contribute to current research and possible future directions are presented.