This July we will introduce you to a comprehensive NLP #DataMeetUp presented by Dr. Preslav Nakov from Qatar Computing Research Institute, HBKU, ranked #8 in the world for NLP and Vesela Gateva from the LinkedIn Data Science team.
The NLP MeetUp
- Automatically distinguishing #fakeNews
- A general-purpose #DeepLearning framework for fully-automatic fact-checking
- The architecture of a system of the winners of Hack the News #Datathon2017 for fake news and clickbait detection
- The stance detection, news source reliability, bias and #propaganda detection
- #TextAnalysis for product categorization and segmentation
Dr. Preslav Nakov will present the problems related to the automatically distinguishing false rumors from factually-true claims. In this MeetUp, he will present several related problems. First, in the context of investigative journalism, he will address the problem of automatically identifying which claims in a political debate are most worthy and should be prioritized for fact-checking (QCRI’s ClaimRank tool: http://claimrank.qcri.org/). He will further extend this framework to the context of community question answering, where the goal is to decide whether an answer to a factual question is factually true or false. He will also describe an application of this framework to the problem of fake news and clickbait detection, presenting the architecture of a system that won the 2017 Datathon on this problem, organized by the Data Science Society. Dr. Nakov will cover some related problems such as stance detection, news source reliability, bias and propaganda detection, as well as finding seminar users and opinion manipulation trolls in news community fora.
Vesela Gateva will cover the end to end process of categorizing a product based on text analysis using NLP and other techniques, its practical and product considerations as well as downstream uses of the categorization.
The first of our special guests will be Dr. Preslav Nakov who is a Senior Scientist at the Qatar Computing Research Institute, HBKU, which is ranked #2 in Asia and #8 in the world in the area of Natural Language Processing. Preslav Nakov’s research interests include computational linguistics and natural language processing (for English, Arabic, and other languages), machine translation, question answering, fact-checking, sentiment analysis, lexical semantics, Web as a corpus, and biomedical text processing.
We are very happy to have Vesela Gateva as our second speaker at the Meetup. Vesela is a Senior Data Scientist at LinkedIn where she is the data science lead for LinkedIn Groups. Prior to LinkedIn, she worked at Eventbrite where her work focused on building various models partnering with Marketing and Finance and before entering the tech world, she worked in the biotech industry doing research in Statistical Genetics where her work focused on studies with the goal of finding genes.