We propose a new webpage ranking algorithm which is personalized. Our idea is to rely on the attention time spent on a document by the user as the essential clue for producing the user-oriented webpage ranking. The prediction of the attention time of a new webpage is based on the attention time of other previously browsed pages by this user. To acquire the attention time of the latter webpages, we developed a browser plugin which is able to record the time a user spends reading a certain webpage and then automatically send that data to a server. Once the user attention time is acquired, we calibrate it to account for potential repetitive occurrences of the webpage before using it in the prediction process. After the user’s attention times of a collection of documents are known, our algorithm can predict the user’s attention time of a new document through document content similarity analysis, which is applied to both texts and images. We evaluate the webpage ranking results from our algorithm by comparing them with the ones produced by Google’s Pagerank algorithm.

Abstract not found

Abstract. In this paper we present NewsFlash, an adaptive search system that assists a searcher to efficiently search a library of stored TV news reports. The system automatically summarises the closed-caption subtitles embedded in the TV broadcasts and selects appropriate sentences to best describe report content in respect to the searcher’s query. During interaction the system selects useful terms from these summaries and uses these terms to update the display and potentially update a stored searcher profile. We evaluate the worth of our approach with real searchers and realistic information seeking scenarios. A novel means of testing the worth of a permanent profile of searchers ’ general interests is also proposed. Our results show that the adaptive techniques we propose can work well in multimedia search environments. 1

Abstract. This paper proposes a new approach to ranking the documents retrieved by a search engine using click-through data. The goal is to make the final ranked list of documents accurately represent users ’ preferences reflected in the click-through data. Our approach combines the ranking result of a traditional IR algorithm (BM25) with that given by a machine learning algorithm (Naïve Bayes). The machine learning algorithm is trained on clickthrough data (queries and their associated documents), while the IR algorithm runs over the document collection. We consider several alternative strategies for combining the result of using click-through data and that of using document data. Experimental results confirm that any method of using click-through data greatly improves the preference ranking, over the method of using BM25 alone. We found that a linear combination of scores of Naïve Bayes and scores of BM25 performs the best for the task. At the same time, we found that the preference ranking methods can preserve relevance ranking, i.e., the preference ranking methods can perform as well as BM25 for relevance ranking. 1

Abstract. Online dating presents a rich source of information for preference learning. Due to the desire to nd the right partner, users are willing to provide very speci c details about themselves and about the people they are looking for. The user can describe his/her ideal partner by specifying values for a set of prede ned attributes. This explicit preference model is quite rigid and may not re ect reality, as users ' actions are often contrary to their stated preferences. In this respect learning implicit user preferences from the users ' past contact history may be a more successful approach for building user preference models for use in recommender systems. In this study, we analyse the di erences between the implicit and explicit preferences and how they can complement each other to form the basis for a recommender system for online dating. 1

In this thesis, we investigate using the Language Modeling approach for ad hoc Information Retrieval as a theoretically principled framework for encoding contextual evidence. Using context to improve retrieval performance is a current challenge within the discipline and presents a major challenge to the research community. The Language Modeling approach provides a natural and intuitive means of encoding the context as-sociated with a document. However, the Language Modeling approach also represents a change to the way probability theory is applied in ad hoc Information Retrieval and makes several assumptions for its application [112, 113, 57, 96]. We consider these assumptions and study them in detail during the course of this thesis. Central to the assumptions is the key implication that better retrieval performance can be obtained through developing better representation of the documents. We posit that the context associated with a document will enable the development of such representations-context based document models. This premise relies upon the explicit and implicit assumptions of the Language Modeling approach being valid, which have, up until now,

Strathprints is designed to allow users to access the research output of the University of Strathclyde. Copyright © and Moral Rights for the papers on this site are retained by the individual authors and/or other copyright owners. Users may download and/or print one copy of any article(s) in Strathprints to facilitate their private study or for non-commercial research. You may not engage in further distribution of the material or use it for any profit-making activities or any commercial gain. You may freely distribute the

We introduce a news retrieval system on which we evaluated three alternative presentation strategies for online news retrieval. We used a user-oriented and task-oriented evaluation framework. The interfaces studied were Image, giving a grid of thumbnails for each story together with query-based summaries presented as tooltips, Summary, which displayed the summary information alongside each thumbnail, and Cluster, which grouped similar stories together and used the same display format as Image. The evaluation showed that the Summary Interface was preferred to the Image Interface, and that the Cluster Interface was helpful to users with a set task to complete. The implications of this study are also discussed in this paper. 1.

In this position paper we present an overview of our current work in utilising contextual models to help web searchers find relevant web documents. The traditional approach to such information retrieval (IR) assumes that a user’s information need is static and does not change as they peruse the documents the search system presents to them. However, this approach is simplistic, and does not consider the dynamic nature of an information need, something that has been well documented. In our approach we use implicit evidence, captured unobtrusively from searcher interaction to model such change. We are particularly interested in the intentionality behind this interaction, and which document representations (i.e. summaries, sentences) users view. This evidence is firstly used to enhance the user’s query, then automatically update the display and if required, re-search the web.

We propose a new document summarization algorithm which is personalized. The key idea is to rely on the attention (reading) time of individual users spent on single words in a document as the essential clue. The prediction of user attention over every word in a document is based on the user’s attention during his previous reads, which is acquired via a vision-based commodity eye-tracking mechanism. Once the user’s attentions over a small collection of words are known, our algorithm can predict the user’s attention over every word in the document through word semantics analysis. Our algorithm then summarizes the document according to user attention on every individual word in the document. With our algorithm, we have developed a document summarization prototype system. Experiment results produced by our algorithm are compared with the ones manually summarized by users as well as by commercial summarization software, which clearly demonstrates the advantages of our new algorithm for user-oriented document summarization.