SIGIR09: Predicting User Interests from Contextual Information

Peter Bailey et al. from Microsoft described a study comparing sources of context in predicting the subsequent interests of a user looking at a particular page.  (A note of caution, the term context in the IR community refers to auxillary text or documents used to augment a query typically to help disambiguate it and improve [...]

SIGIR09: Telling Experts from Spammers: Expertise Ranking in Folksonomies

From our friends in Southhampton (correction: and Hasso-Platner), a study of how to differentiate experts (who really know how to tag stuff) from spammers (who want to tag their own stuff, but try to acquire credibility by copying tags others have used).   They try to exploit the difference that the people who tag first are [...]

SIGIR09: The Wisdom of the Few: A Collaborative Filtering Approach Based on Expert Opinions from the Web

Xavier Amatriain of Telefonica research presented work on collaborative filtering.  Usually you do collaborative filtering by finding the other users “similar” to your subject and combining their recommendations.  This paper argued/demonstrated that sometimes you are better off figuring out who the experts art and only paying attention to their opinions.  You might just create [...]

SIGIR09: An Aspectual Interface for Supporting Complex Search Tasks

Robert Villa of U. Glasgow presented. They consider how broad complex tasks can be supported through a search interface, covering the multiple subtasks someone might need to perform—e.g., investigating several candidate resources in the middle of the search, or, doing multiple related searches. They developed an interface that let users create and [...]

SIGIR09: a comparison of query and term suggestion features for interactive searching

Diane Kelley of UNC Chapel Hill presented some interfaces for helping users refine their queries. Lots of situations arise where people need to enter a series of queries to home in on what they are looking for. Literature shows people can exhaust their ideas for good search queries. IR has explored techniques [...]

SIGIR09: Search Engine Predeliction Towards News Media Providers

I saw a nice poster from U. Glasgow which shows that different search engines exhibit different biases on which news media providers are returned as results for various queries. E.g., one search engine avoids New York Times, another avoids Reuters. They can’t tell whether these biases are intentional or side effects of ranking [...]

SIGIR09: Enhancing Cluster Labeling using Wikipedia

David Carmel from IBM Haifa spoke about the problem of labelling document clusters.  The goal is to find short labels for the clusters that describe them well to end users.  The typical approach seeks important terms in the clusters.  But sometimes important terms aren’t helpful/meaningful, and sometimes the best labels don’t show up in the [...]

SIGIR09: simultaneously medeling semantics and structure of threaded discussions

A group from SMR asia is working on modeling threaded discussions.  Threaded discussions pervade IMs, chat rooms, web forums, and mailing lists.  They’re hierarchical.  This group wants to mine the semantics (discover the topics) and the structure (author-reply relationships). The applications include spam blocking, reply constructions (figuring out which specific posts other posts are replying [...]

Using implicit user feedback for improving IR (SIGIR'09)

(Liveblogged from SIGIR’09 Boston)
In the first session of the first day of SIGIR’09 Boston, three papers presented approaches at using implicit user actions (activities) for improving information retrieval precision.  Here is a brief summary:
Queries from Activities in Daily Living – Takuya Maekawa (NTT Japan) presented work describing using RFID sensors embedded in devices in [...]

SIGIR09: A Statistical Comparison of Tag and Query Logs

Mark Carman presented on the paper in the title.  They’re interested in studying personalization, but for that they need personalized relevance judgements.  Query logs are a great source of that information but aren’t available due to privacy concerns.  So they started looking at whether tag data (public) could be used as a substitute for query [...]