W18: Workshop on Domain-Adaptive Methods for Text Analytics, Sentiment Analysis, and Opinion Mining
Organizers: William Hsu and Chengxiang Zhai
WORKSHOP OVERVIEW This workshop will address the problem of adapting across domains and extracting information from the large volume of text written in blogs, mailing lists, forums, and other electronic venues, then making this information accessible via structured queries, while analyzing it to map out patterns among the opinions and demographics of users. Information retrieval systems exist for spatially-referenced demographic data, but the databases that contain such data are manually populated. For example, in information portals such as HealthMap.org, which are searchable by location and disease, the data are user-reported and collaboratively maintained, but not automatically extracted from text. Furthermore, there is as yet no automated means of relating sentiments expressed by users in their text postings to their semistructured profile data. This is because the primary sources for this kind of information have been statistical surveys such as opinion polls, where text responses are often human-interpreted and demographic analysis is done post hoc, rather than as part of an information retrieval and extraction task. These limitations indicate a present need for text summarization techniques that integrate quantitative information extraction - which captures symptoms, diseases, and complications of diseases - with opinion summarization. This workshop shall help to bring together people from these different areas and present an opportunity for researchers and practitioners to share new techniques for identifying and analyzing relationships in networks that integrate multiple types or sources of information. Both technical papers and position papers exploring key aspects of the state of the field in domain adaptation are welcome. WORKSHOP AUDIENCE We welcome paper submissions from researchers in all areas of domain adaptation in text analytics, particularly: * Topic modeling * Polarity (by classification and regression) * Sentiment analysis * Opinion mapping * Higher-level tasks: question answering (QA) and knowledge-base population specific to opinions We also hope to attract IJCAI participants from industrial R&D with interesting current applications that showcase aspects of domain adaptation in social media (upvotes/likes and shares/retweets, tweets and status updates, forum and blog posts, etc.).