Miles Efron posted recently on his take on the progress of the IR field in response to a question posted by Andrew Dillon at the last ASIST conference. Miles’ take was that progress was indeed being made for two reasons: the SIGIR conference has become more competitive over the years, and the diversity of corpora in the TREC umbrella has also increased. Unfortunately, I wasn’t there to hear the question or the subsequent discussion, but my guess as to what Andrew Dillon actually meant was not a question of statistical significance, but rather one of magnitude.

Continue Reading

Marti Hearst‘s new book, Search User Interfaces, is out, as Daniel Tunkelang reported earlier. The book covers a range of topics related to interaction around information seeking, including topics such as design, evaluation, models of information seeking, query reformulation, etc. It also discusses emerging trends: Mobile Search Interfaces, Multimedia (although this field has arguably been around long enough to no longer be emerging), Social Search, and natural-language queries. The Social Search section discusses collaborative filtering, recommendation systems, and collaborative search, describing several systems along the full range of depth of mediation.

Continue Reading

In their JCDL 2009 paper titled “Cost and Benefit Analysis of Mediated Enterprise Search” Wu et al. described a cost-benefit analysis of call center activity. The goal was to understand when an experts should help “consultants” who are handling phone calls from customers. The idea was that experts could make improvements in search results of queries run by consultants by identifying useful documents; the challenge is to make effective use of the more expensive experts’ time.

This seems like a great opportunity to implement a collaborative search interface that would mediate the collaboration between the people handling the phone calls and the technical experts. In addition to screen sharing (to help the expert understand the problem), the system might provide the expert with additional tools to facilitate searches and to reuse previously-found results.

Looks like I missed a good paper at JCDL 2009: A Polyrepresentational Approach to Interactive Query Expansion by Diriye, Blandford and Tombros. As with many good ideas, this paper describes an approach that is obviously useful once described, but one I had not come across before.

Manual query expansion can be useful when relevance feedback fails because it doesn’t know why a person found a document relevant, but people are often reluctant to use the suggestions offered by information seeking systems. This paper offers a new twist on these recommended terms: When suggesting query terms for expanding a user’s queries, they show terms with some representation of the context in which they occur. Evaluation showed that this contextual information allowed users to understand query terms better, and that it improved their ability to make relevance judgments with respect to documents that contained the suggested terms.

In Cerchiamo, we offered users term suggestions based on relevance judgments made by search partners. While the suggested terms were useful for identifying other relevant documents, they weren’t always used. It’s likely that term recommendation in collaborative search situations would benefit from these techniques even more than in the standalone search because in the collaborative search case term recommendations may be based on documents that a searcher has never seen.

Bill Kules and Robert Capra have an interesting poster at JCDL 2009. “Designing Exploratory Search Tasks for User Studies of Information Seeking Support Systems” describes a study that evaluated an algorithm for determining whether a search task makes a good exploratory or known-item search candidate. They evaluated their approach by having 18 study participants run candidate queries (four exploratory and two known-item). After performing the specified searches, participants answered the questions about

1. Familiarity with the topic
2. Topic difficulty
3. Their confidence that the task was fulfilled
4. The degree to which answering the question required finding multiple documents
5. The extent that the person’s understanding of the topic changed during the session

The study reported the following significant differences between the two conditions: People said that they found exploratory tasks more difficult, they had lower confidence that the task was fulfilled, they had to find multiple documents to fulfill the request, and their goals changed during the search session.

This is a nice summary of the distinctions between exploratory search and known-item or navigational searches, and underscores the need to build interfaces that support the differences among these tasks.

Update:  The poster one page description is now online, as is the poster handout.

Brynn Evans has been doing some interesting research on looking at how social networks support collaboration over information seeking. She uses two dimensions—search goals and search locations—and looks at how social interactions affect search activities, and discusses the implications that this work has for the design of tools to support information seeking. Slides are available through SlideShare, and a video of the talk is also online.

Continue Reading

Arguably the two most common topics on this blog are search, especially collaborative exploratory search, and virtual worlds. Now, the new browser-based 3D platform ExitReality, has piqued my curiosity by bringing these topics together. As part of their 3D platform, they offer a search engine optimized for finding and displaying 3D objects and worlds. You can either enter the found 3D sources as a world entire unto itself, or (my favorite) drag-n-drop it into your current 3D space in the browser window. (If you’d like to see the 3D search via a normal 2D web page, that’s available here.)

Note that this 3D search engine is one that searches for 3D objects, models etc., not something like the SpaceTime browser that displays standard search results in a 3D(ish) format.

So it was this morning I found myself standing with a wizard, a Doberman and a rat on the outskirts of Stonehenge, contemplating several quite nice Moon lander models and a gigantic purple flower (Cattleya – one of the search results for “cat”). This all in the space of ten minutes’ carefree clicking around. Dali would’ve had a ball.

Browser-based 3D with 3D search engine

ExitReality’s tag line is “the entire Web in 3D.” The idea is you can convert your own website to 3D via a fairly simple process – and it’ll still look the same in 2D; you’ve just added a 3D button. In general the interface is very well thought out – where it falters is most likely due to its beta status (e.g. avatars can’t yet fly or change clothes, though you can change avatars).

My second favorite feature so far: when other people visit the web site you’re viewing, you see them as avatars (if they have ExitReality installed). It’s possible to use in a standalone kiosk mode, or in secure mode behind a firewall. My first favorite feature? Check this space tomorrow for details.

First, I agree with Daniel Tunkelang and many others that this is an important step for Google, an important departure from the ranked list. Hurray! My sense about this way of performing exploratory search is that Google Squared addresses (at least) two different kinds of activity: filtering through structured data, and collecting different instances of some topic. The former, of interest to the set-oriented retrieval crowd, should make it easier to do feature comparison for a variety of domains, typically with some sort of a shopping angle. In this post, I will focus on the second kind, the less structured exploratory search. Continue Reading

I wasn’t able to attend or contribute to the Collaborative Information Behavior (CIB) workshop held recently in conjunction with the GROUP 2009 conference, and was looking forward to reading about the discussion, which was posted today by Sharoda Paul.  The discussion touched on several interesting points, and perhaps we can get some of the participants to comment more on them (here or elsewhere). The notes highlight discussion around models, behavior vs. technical design, appropriate research methods, explicit vs. implicit collaboration (yeah!), and evaluation.

Continue Reading

I’m taking Bing for a spin. I’ve changed my default search engine to Bing, and am going to give a try. I am not particularly interested to see if it has  better ranking than Google. It probably won’t matter but for a few cases anyway.

What I am more interested in are the various navigational and finding aids that have been incorporated into the search engine’s interface. So far, I’ve seen the following interesting aspects: Continue Reading