The First International Workshop on Recent Trends in News Information Retrieval will take place in Padua, Italy in conjunction with ECIR 2016.
In this talk, I report on some recent advances of the Corporate R&D group at Thomson Reuters. Thomson Reuters is divided into the business areas News, Legal, Financial & Risk, Tax & Accounting, IP & Science. In the realm of news, the news recommender system NewsPlus and the real-time Twitter rumor detection tool for journalists, REUTERS Tracer, are discussed. From the area of pharma within IP & Science, I review work on adverse events associated with medical drugs, as mined from Twitter and used for drug repositioning. From the area of law, I report on the advanced search engine technology that powers the Westlaw search engine. From the area of Financial & Risk, I present risk mining, a technique for computer-supported risk identification framed as a relation classification task. Last but not least I conclude with some observed challenges and lessons learned. I conclude with a series of challenges and needs for the news industry.
Dr. Jochen Leidner is currently Director of Research at Thomson Reuters, where he heads the London (UK) R\&D site, which he established. He has worked in many areas including information extraction from legal, news and financial documents, search engine technology and its application to legal information retrieval, automated proofing support for contracts, sentiment analysis, rule based systems, citation analysis and social media.
Monitoring Online Reputation has already become a key part of Public Relations for organizations and individuals; and current search technologies do not suffice to help reputation experts to cope with the vast stream of online content flooding reputation management experts. In the talk we will summarize some of the main challenges that Information Access Technologies must face to assist online reputation monitoring tasks, and present some of the results obtained by the UNED research group in the areas of entity name disambiguation, topic tracking for reputation analysis, identification of opinion makers, and reputation-oriented summarization. We will make a special emphasis on the Replab test collections for Online Reputation Monitoring, which provide over half a million manual annotations provided by reputation experts on Twitter data.
Dr. Julio Gonzalo (UNED, Madrid, Spain) is head of the UNED research group in Natural Language Processing and IR (nlp.uned.es). He has recently been co-organizer of the RepLab Evaluation Campaign for Online Reputation Management Systems, co-organizer of the WePS evaluation campaign for Web People Search systems, and co-recipient of a Google Faculty Research Award. His research interests include Entity-Oriented and Semantic Search, Evaluation Methodologies and Metrics in Information Access, and Information Access Technologies for Social Media. A list of his publications can be found at Google Scholar: