A generative blog post retrieval model that uses query expansion based on external collections
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
A two-stage model for blog feed search
Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
| Hi-index | 0.00 |
Since its introduction, social media, "a group of internet-based applications that (...) allow the creation and exchange of user generated content" [1], has attracted more and more users. Over the years, many platforms have arisen that allow users to publish information, communicate with others, connect to like-minded, and share anything a users wants to share. Text-centric examples are mailing lists, forums, blogs, community question answering, collaborative knowledge sources, social networks, and microblogs, with new platforms starting all the time. Given the volume of information available in social media, ways of accessing this information intelligently are needed; this is the scope of my research. Why should we care about information in social media? Here are three examples that motivate my interest. (A) Viewpoint research; someone wants to take note of the viewpoints on a particular issue. (B) Answers to problems; many problems have been encountered before, and people have shared solutions. (C) Product development; gaining insight into how people use a product and what features they wish for, eases the development of new products. Looking at these examples of information need in social media, we observe that they revolve not just around relevance in the traditional sense (i.e., objects relevant to a given topic), but also around criteria like credibility, authority, viewpoints, expertise, and experiences. However, these additional aspects are typically conditioned on the topical relevance of information objects. In social media, "information objects" come in several types but many are utterances created by people (blog posts, emails, questions, answers, tweets). People and their utterances offer two natural entry points to information contained in social media: utterances that are relevant and people that are of interest. I focus on three tasks in which the interaction between the two is key.