Search results

Examines the use of query reformulation, and particularly the use of relevance feedback by users of the Excite Web search engine. A total of 985 user search sessions from a data set of 18,113 user search sessions containing 51,473 queries were examined. Includes a qualitative and quantitative analysis of 191 user sessions including more than one query, to examine patterns of user query reformulation; and second, all 804 user sessions including relevance feedback were examined. Results show limited use of query reformulation and relevance feedback by Excite users – only one in five users reformulated queries. Most relevance feedback sessions were successful. Identifies the most common pattern of searching and discusses implications for Web search system design.

This paper reports experiments with a term weighting model incorporating relevance information in which it is assumed that index terms are distributed dependently. Initially this model was tested with complete relevance information against a similar model which assumes index terms are distributed independently. The experiments demonstrated conclusively that index terms are not independent for a number of diverse document collections. It was concluded that the use of relevance information together with dependence information could potentially improve retrieval effectiveness. As a result of further experiments the initial strict dependence model was modified and in particular a new relevance‐based term weight was developed. This modified dependence model was then used as the basis for relevance feedback, i.e. with partial relevance information only, and significant increases in retrieval effectiveness were achieved. The evaluation method used in the feedback experiments emphasized the effect of the feedback on documents which the potential user would not previously have seen. Finally the incorporation of relevance feedback in an operational system is considered and in particular it is argued that if high recall searches are required, relevance feedback based on the modified dependence model may be superior to the widely used Boolean search.

The term relevance weighting method has been shown to produce optimal information retrieval queries under well‐defined conditions. Unfortunately, the relevance weights cannot be determined in the absence of accurate knowledge of the occurrence frequencies of the terms in the relevant and non‐relevant documents of a collection. This study presents a realistic method for estimating the term relevance weights from information derived in an interactive search environment where relevance assessments for previously retrieved items are used later to construct improved query statements. Procedures are introduced for constructing the initial query weights by using estimated term relevance factors. These initial weights are then modified during the relevance feedback process by utilizing the occurrence frequencies of the terms in the retrieved documents obtained from an earlier search. The procedures used to construct the term relevance weights are covered in detail, and experimental output is included to illustrate the effectiveness of the methods.

Conventional studies mainly classify a term’s appearance in the retrieved documents as either relevant or irrelevant for application. The purpose of this paper is to differentiate the term’s appearances in the retrieved documents in more detailed situations to generate relevance information and demonstrate the applicability of the derived information in combination with current methods of query expansion.

A method was designed first to utilize the derived information owing to term appearance differentiation within a conventional query expansion approach that has been proven as an effective technology in the enhancement of information retrieval. Then, an information retrieval system was developed to demonstrate the realization and sustain the study of the method. Formal tests were conducted to examine the distinguishing capability of the proposed information utilized in the method.

The experimental results show that substantial differences in performances can be achieved between the proposed method and the conventional query expansion method alone.

Since the proposed information resides at the bottom of the information hierarchy of relevance feedback, any technology regarding the application of relevance feedback information could consider the utilization of this piece of information.

The importance of the study is the disclosure of the applicability of the proposed information beyond current usage of term appearances in relevant/irrelevant documents and the initiation of a query expansion technology in the application of this information.

The purpose of this paper is to improve users’ search results relevancy by manipulating their explicit feedback.

CoRRe – an explicit feedback model integrating three popular feedback, namely, Comment-Rating-Referral is proposed in this study. The model is further enhanced using case-based reasoning in retrieving the top-5 results. A search engine prototype was developed using Text REtrieval Conference as the document collection, and results were evaluated at three levels (i.e. top-5, 10 and 15). A user evaluation involving 28 students was administered, focussing on 20 queries.

Both Mean Average Precision and Normalized Discounted Cumulative Gain results indicate CoRRe to have the highest retrieval precisions at all the three levels compared to the other feedback models. Furthermore, independent t-tests showed the precision differences to be significant. Rating was found to be the most popular technique among the participants, producing the best precision compared to referral and comments.

The findings suggest that search retrieval relevance can be significantly improved when users’ explicit feedback are integrated, therefore web-based systems should find ways to manipulate users’ feedback to provide better recommendations or search results to the users.

The study is novel in the sense that users’ comment, rating and referral were taken into consideration to improve their overall search experience.

A primary function of the Performance Measurement System is to provide employees with information on their past performance, allowing them to assess the outcomes of their actions, and therefore if they are meeting or not the objectives they are given. This work aims at contributing to the understanding of how the effectiveness of performance feedback information can be improved by defining a set of distinct performance feedback dimensions based on a PMS literature review, and by validating it empirically on an international sample of 164 manufacturing organisations. The proposed dimensions are: relevance as performance feedback orientation to the achievement of objectives; dynamic adjustment of performance feedback; relevance as usefulness of cost performance feedback; relevance as usefulness of non‐cost performance feedback; timeliness of shop‐floor performance feedback; personal performance feedback; and feedback on the overall process performances. The analysis shows that these dimensions are distinct, thus allowing to deal with them separately both in PMS design and audit. As far as the effectiveness of the performance feedback is concerned, it emerges that for several dimensions higher scores are associated to higher operating performances (cost, time and quality), but in one case this only holds for managers and in another one only for supervisors.

This paper reports on the successful introduction of a sophisticated online catalogue system at the library of the Scott Polar Research Institute, Cambridge, using the Muscat program package. The system provides to both end‐users and library staff a choice between boolean searching on keywords and access using relevance feedback based on free text in English, mixed with UDC classification numbers. The system is implemented on an IBM 3084 computer. Significant benefits from the application of relevance feedback are reported with 10,000 records on file.

An important issue in the management of a web‐based user community, where users are registered to a web portal, is to identify patterns of users' interest. In this context, the users' feedback plays a major role. The purpose of this paper is to define a novel framework analysis for managing the feedback given by registered visitors of a web site.

The paper presents a new technique to integrate the feedback explicitly given by users into already existing user profiles. The authors introduce the novel concepts of scope, filtering, and relevance profiles for managing users' feedback. The new concept of Relevance Profile (RP) is defined.

Using the framework, the authors were able to discover patterns of usage of registered users of a web site.

The practical applicability of the approach is validated by a use case study showing how the framework can be used with a real web site. The authors used Gugubarra as a reference system, a prototype for creating and managing web user profiles, developed by the DBIS group at the Goethe‐University of Frankfurt.

A new way to integrate the user feedback into interest profiles and a novel framework to analyze and discover patterns of interests are presented. The paper is an extended version (more than 50 per cent novel material) of a previous paper presented at the iiWAS2010 conference.

A total of 17 user‐compiled collections of webpages, comprising 833 bookmarked links in terms of genre, are studied. The purpose of this paper is to find out whether users tend to bookmark certain web genres more than others. Genre theory helps to make sense of the different pages included in these collections, and to classify them, according to their communicative purpose and salient non‐topical features, into blogs, search interfaces, articles, tutorials.

A total of 17 participants took part in the research by providing their collections of bookmark links. They were also interviewed about the reasons for bookmarking and to comment on their collections. Relying on the interview results and on the previous literature, the bookmarks were classified into four super‐genres: main or access pages, transactional pages, navigational pages, and content pages.

The results of the classification into web genres revealed a clear tendency to bookmark main pages, such as homepages, which accounted for 42 per cent of all bookmarked web links. Moreover, some aspects of relevance were highlighted such as the connections to use, time, and context, as well as to the main web activity (browsing or searching).

Previously, bookmarks have mostly been studied as tools for information reuse, but very rarely as sources of implicit relevance feedback. In addition, from the point of view of genre theory, this research shows the importance of relating web genres to users' intentions behind queries.

Much previous research on improving information retrieval applications has focused on developing entirely new systems with advanced searching features. Unfortunately, most users seldom utilize these advanced features. This research explores the use of a software agent that assists the user during the search process. The agent was developed as a separate, stand‐alone component to be integrated with existing information retrieval systems. The performance of an information retrieval system with the integrated agent was subjected to an evaluation with 30 test subjects. The results indicate that agents developed using both results from previous user studies and rapidly modeling user information needs can result in an improvement in precision. Implications for information retrieval system design and directions for future research are outlined.