Mobile delivery of news using hierarchical query-biased summaries

Abstract

This paper presents the results of a study aimed at measuring the usefulness of presenting the results of an Information B~trieval search on WAP mobile phones. The experimentation focuses on presenting automatically-generated summaries of newspaper articles of increasing length on a mobile phone interface and in studying the differences in users' perception of relevance of the retrieved documents. The aim is to study experimentally how users' perception of relevance varies depending on the length of the summary, and in relation to the specific characteristic of the mobile interface that content is presented. Experimental results suggest that hierarchical query biased summaries are useful when dealing with small screens and assist users in making correct relevance judgments.

Supporting Searching on Small Screen Devices Using Summarisation

“…Questionnaires completed by the users suggest that hierarchical query-biased summaries are useful and assist users in making relevance judgments. The results are consistent with the findings of our previous study that found for small screen displays (WAP mobile phone interface) users showed both a preference and better performance with the shorter summary lengths (7% of the document length) [20]. Further support for presenting concise relatively brief summaries on small screen devices comes from the findings of a recent WAP usability study 7 .…”

“…phone interface [20]. In particular, the average levels of precision are similar to those found when documents summaries are presented to a user on a computer screen [22] but have slightly lower levels of recall.…”

“…Extending the forms of presentation to include small screen devices, Sweeney, Tombros and Crestani looked at the use of query-biased hierarchical based summaries of newspaper articles presented to users on WAP mobile phones [20]. Defining hierarchical summaries as summaries of variable length, increasing from title only, 7%, 15%, to 30% of the original document length, the study investigated how users' perception of relevance varied depending on the length of the summary, and in relation to the specific characteristic of a typical WAP mobile phone interface.…”

“…We use the same experimental procedure to the study previously mentioned [20], again using the hierarchical query-biased summaries, however, in this study we shall focus on the effects due to displaying content on a PDA interface. Again we are interested in assessing the variation of user performance in evaluating the relevance of full documents, given hierarchical query-biased summaries, and also determining whether there is an optimal size of summary for this type of interface.…”

“…The summarisation system used to produce the summaries for the experiment was the same as that described in [20]. The system uses a number of sentence extraction methods [15] that utilise information both from the documents of the collection and from the queries used.…”