SocialNLP@WWW 2018 Chairs' Welcome & Organization

Abstract

With the rapid growing of social networking services (e.g., Facebook and Twitter), being able to process data come from such platforms has gained much attention in recent years. SocialNLP is a new inter-disciplinary area of natural language processing (NLP) and social computing. There are three plausible directions of SocialNLP: (1) addressing issues in social computing using NLP techniques; (2) solving NLP problems using information from social media; and (3) handling new problems related to both social computing and natural language processing. Several challenges are foreseeable in SocialNLP. First, the message lengths on social media are usu-ally short, and thus it is difficult to apply traditional NLP approaches directly. Second, social media contains heterogeneous information (e.g. tags, friends, followers, likes, and retweets) that should be considered together with the contents for better quality of analysis. Finally, social media contents always involve multiple persons with slangs and jargons, and usually require special techniques to process. We organize SocialNLP in WWW 2018 with three goals. First, social media data is essentially generated and collected from online social services that are functioned based on Web techniques. One can leverage Web techniques to investigate various user behaviors and investigate the interactions between users. Second, user-generated data in social media is mainly in the form of text. Theories and techniques on Web information retrieval and natural language processing are desired for semantic understanding, accurate search, and efficient processing of big social media data. Third, from the perspective of application, if social media data can be effectively processed to distill the collective knowledge of users, novel Web applications, such as emergency management, social recommendation, and future prediction, can be developed with higher accuracy and better user experience. We expect SocialNLP workshop in WWW community can provide mutually-reinforced benefits for researchers in areas of Web techniques, information retrieval and social media analytics.