Search

This paper proposes the usage of \emph{visualisation widgets} for exploratory search with \emph{sentiment} as a facet. Starting from specific design goals for depiction of ambivalence in sentiment, two visualization widgets were implemented: \emph{scatter plot} and \emph{parallel coordinates}. Those widgets were evaluated against a text baseline in a small-scale usability study with exploratory tasks using Wikipedia as dataset. The study results indicate that users spend more time browsing with scatter plots in a positive way. A post-hoc analysis of individual differences in behavior revealed that when considering two types of users, \emph{explorers} and \emph{achievers}, engagement with scatter plots is positive and significantly greater \textit{when users are explorers}. We discuss the implications of these findings for sentiment-based exploratory search and personalised user interfaces., Comment: Presented at the Social Personalization Workshop held jointly with ACM Hypertext 2014. 6 pages

Anyone offering content in a digital library is naturally interested in assessing its performance: how well does my system meet the users' information needs? Standard evaluation benchmarks have been developed in information retrieval that can be used to test retrieval effectiveness. However, these generic benchmarks focus on a single document genre, language, media-type, and searcher stereotype that is radically different from the unique content and user community of a particular digital library. This paper proposes to derive a domain-specific test collection from readily available interaction data in search logs files that captures the domain-specificity of digital libraries. We use as case study an archival institution's complete search log that spans over multiple years, and derive a large-scale test collection. We manually derive a set of topics judged by human experts--based on a set of e-mail reference questions and responses from archivists--and use this for validation. Our main finding is that we can derive a reliable and domain-specific test collection from search log files.

In this paper, we document our efforts at INEX 2007 where we participated in the Ad Hoc Track, the Link the Wiki Track, and the Interactive Track that continued from INEX 2006. Our main aims at INEX 2007 were the following. For the Ad Hoc Track, we investigated the effectiveness of incorporating link evidence into the model, and of a CAS filtering method exploiting the structural hints in the INEX topics. For the Link the Wiki Track, we investigated the relative effectiveness of link detection based on retrieving similar documents with the Vector Space Model, and then filter with the names of Wikipedia articles to establish a link. For the Interactive Track, we took part in the interactive experiment comparing an element retrieval system with a passage retrieval system. The main results are the following. For the Ad Hoc Track, we see that link priors improve most of our runs for the Relevant in Context and Best in Context Tasks, and that CAS pool filtering is effective for the Relevant in Context and Best in Context Tasks. For the Link the Wiki Track, the results show that detecting links with name matching works relatively well, though links were generally under-generated, which hurt the performance. For the Interactive Track, our test-persons showed a weak preference for the element retrieval system over the passage retrieval system.

This paper gives an overview of the INEX 2007 Ad Hoc Track. The main purpose of the Ad Hoc Track was to investigate the value of the internal document structure (as provided by the XML mark-up) for retrieving relevant information. For this reason, the retrieval results were liberalized to arbitrary passages and measures were chosen to fairly compare systems retrieving elements, ranges of elements, and arbitrary passages. The INEX 2007 Ad Hoc Track featured three tasks: For the Focused Task a ranked-list of non-overlapping results (elements or passages) was needed. For the Relevant in Context Task non-overlapping results (elements or passages) were returned grouped by the article from which they came. For the Best in Context Task a single starting point (element start tag or passage start) for each article was needed. We discuss the results for the three tasks, examine the relative effectiveness of element and passage retrieval. This is examined in the context of content only (CO, or Keyword) search as well as content and structure (CAS, or structured) search.

The following paper proposes a new kind of relevance feedback. It shows how so-called query profiles can be employed for disambiguation and clarification. Query profiles provide useful summarized previews on the retrieved answers to a given query. They outline ambiguity in the query and when combined with appropriate means of interactivity allow the user to easily adapt the final ranking. Statistical analysis of the profiles even enables the retrieval system to automatically suggest search restrictions or preferences. The paper shows a preliminary experimental study of the proposed feedback methods within the setting of TREC's interactive HARD track.

We introduce two metrics aimed at evaluating systems that select facetvalues for a faceted search interface. Facetvalues are the values of meta-data fields in semi-structured data and are commonly used to refine queries. It is often the case that there are more facetvalues than can be displayed to a user and thus a selection has to be made. Our metrics evaluate these selections based on binary relevant assessments for the documents in a collection. Both our metrics are based on Normalized Discounted Cumulated Gain, an often used Information Retrieval metric.

An abstract is not available

This position paper provides an overview of work conducted and an outlook of future directions within the field of Information Retrieval (IR) that aims to develop novel models, methods and frameworks inspired by Quantum Theory (QT).

Περιέχει το πλήρες κείμενο All search happens in a particular context—such as the particular collection of a digital library, its associated search tasks, and its associated users. Information retrieval researchers usually agree on the importance of context, but they rarely address the issue. In particular, evaluation in the Cranfield tradition requires abstracting away from individual differences between users. This paper investigates if we can bring some of this context into the Cranfield paradigm. Our approach is the following: we will attempt to record the “context” of the humans already in the loop—the topic authors/assessors—by designing targeted questionnaires. The questionnaire data becomes part of the evaluation test-suite as valuable data on the context of the search requests.We have experimented with this questionnaire approach during the evaluation campaign of the INitiative for the Evaluation of XML Retrieval (INEX). The results of this case study demonstrate the viability of the questionnaire approach as a means to capture context in evaluation. This can help explain and control some of the user or topic variation in the test collection. Moreover, it allows to break down the set of topics in various meaningful categories, e.g. those that suit a particular task scenario, and zoom in on the relative performance for such a group of topics.

Mobile and Web 2.0 technology have the very real potential to democratize the creation and sharing of multimedia content in developing communities, even beyond the levels currently seen in community radio and television. In this article, we report the ªndings of an exercise to test this potential in partnership with a Budikote village in southern India. We show how a system called StoryBank supported the creation of short digital stories on a text-free camera phone, and how these stories could be shared through a community repository and touch-screen display. Despite the success of a ªeld trial in which 137 stories were created and shared over a one-month period, various technical and social factors meant that the devices and content were more hierarchically managed and controlled than expected. The implications of these experiences for rural development and community-centered design are discussed.

Traditional document retrieval has shown to be a competitive approach in XML element retrieval, which is counter-intuitive since the element retrieval task requests all and only relevant document parts to be retrieved. This paper conducts a comparative analysis of document and element retrieval, highlights the relative strengths and weaknesses of both approaches, and explains the relative effectiveness of document retrieval approaches at element retrieval tasks.

This book constitutes the thoroughly refereed post-conference proceedings of the 6th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2007, held at Dagstuhl Castle, Germany, in December 2007. The 37 revised full papers presented were carefully reviewed and selected for presentation at the workshop from 50 initial submissions. The papers are organized in an ad hoc track and 6 topical sections on book search, XML-mining, entity ranking, interactive, link-the-wiki, and multimedia.

This paper describes the official measures of retrieval effectiveness that are employed for the Ad Hoc Track at INEX 2007. Whereas in earlier years all, but only, XML elements could be retrieved, the result format has been liberalized to arbitrary passages. In response, the INEX 2007 measures are based on the amount of highlighted text retrieved, leading to natural extensions of the well-established measures of precision and recall. The following measures are defined: The Focused Task is evaluated by interpolated precision at 1% recall (iP[0.01]) in terms of the highlighted text retrieved. The Relevant in Context Task is evaluated by mean average generalized precision (MAgP) where the generalized score per article is based on the retrieved highlighted text. The Best in Context Task is also evaluated by mean average generalized precision (MAgP) but here the generalized score per article is based on the distance to the assessor's best-entry point.

International audience; This paper describes the official measures of retrieval effectiveness employed at the ad hoc track of INEX 2006.

The INEX Multimedia track focuses on using the structure of XML documents to extract, relate, and combine the relevance of different multimedia fragments. This paper presents a brief overview of the track for INEX 2007, including the track's test collection, tasks, and goals. We also report the approaches of the participating groups and their main results.

As part of the INEX 2006 Adhoc Track, we conducted a range of experiments with filtering and clustering XML element retrieval results. Our basic retrieval engine retrieves arbitrary elements from the collection (corresponding to the Thorough Task). These runs are filtered to remove textual overlap between elements (corresponding to the Focused Task). The resulting runs can be clustered per article (corresponding to the All in Context Task). Finally, we select the “best” element for each article (corresponding to the Best in Context Task). Our main findings are the following. First, a complete element index outperforms a restricted index based on section-structure, albeit the differences are small. Second, grouping non-overlapping elements per article does not lead to performance degradation, but may improve scores. Third, all restrictions of the “pure” element runs (by removing overlap, by grouping elements per article, or by selecting a single element per article) lead to some but only moderate loss of precision.

CWI and University of Twente used PF/Tijah, a flexible XML retrieval system, to evaluate structured document retrieval, multimedia retrieval, and entity ranking tasks in the context of INEX 2007. For the retrieval of textual and multimedia elements in the Wikipedia data, we investigated various length priors and found that biasing towards longer elements than the ones retrieved by our language modelling approach can be useful. For retrieving images in isolation, we found that their associated text is a very good source of evidence in the Wikipedia collection. For the entity ranking task we used random walks to model multi-step relevance propagation from the articles describing entities to all related entities and further.

The natural representation of XML data is to use the underlying tree structure of the data. When analyzing these trees we are ensured that no structural information is lost. These tree structures can be efficiently analyzed due to the existence of frequent pattern mining algorithms that works directly on tree structured data. In this work we describe a classification method for XML data based on frequent attribute trees. From these frequent patterns we select so called emerging patterns, and use these as binary features in a decision tree algorithm. The experimental results show that combining emerging attribute tree patterns with standard classification methods, is a promising combination to tackle the classification of XML documents.

This paper discusses our participation in INEX using the TIJAH XML-IR system. We have enriched the TIJAH system, which follows a standard layered database architecture, with several new features. An extensible conceptual level processing unit has been added to the system. The algebra on the logical level and the implementation on the physical level have been extended to support phrase search and structural relevance feedback. The conceptual processing unit is capable of rewriting NEXI content-only and content-and-structure queries into the internal form, based on the retrieval model parameter specification, that is either predefined or based on relevance feedback. Relevance feedback parameters are produced based on the data fusion of result element score values and sizes, and relevance assessments. The introduction of new operators supporting phrase search in score region algebra on the logical level is discussed in the paper, as well as their implementation on the physical level using the pre-post numbering scheme. The framework for structural relevance feedback is also explained in the paper. We conclude with a preliminary analysis of the system performance based on INEX 2004 runs.

Document-centric XML is a mixture of text and structure. +With the increased availability of document-centric XML content comes a need for query facilities in which both structural constraints and constraints on the content of the documents can be expressed. This has generated considerable interest in both the IR and DB communities, and has lead to the launch of evaluation efforts tailored for XML documents. One of the driving and long-standing research questions here is: How does the increased expressiveness of languages for querying XML documents help users to better, and more effectively, express their information needs? And closely related to this: How should we evaluate systems that enable users to express their information needs using both content and structural constraints? In this paper we address these research questions. Our analysis follows two lines: What requirements can in principle be expressed in query languages for document-centric XML documents? And: How do users actually use such languages? For the former, we provide mathematical characterizations of two query languages, one for users with next to no knowledge of the document structure (ignorant users), and one for users that have some, but not complete, knowledge of the document structure (semi-ignorant users). To address the latter issue, we examine the topics formulated in the second query language as part of the 2004 edition of the INEX XML retrieval initiative. Our main findings are as follows: First, while structure is used in varying degrees of complexity, over half of the queries can be expressed in the very restrictive ignorant user language. Second, structure is used as a search hint, and not a search requirement, when judged against the underlying information need. Third, the use of structure in queries functions as a precision device. Fourth, the underlying retrieval task of content-and-structure querying is no different from the ordinary natural language query retrieval task. From those findings we derive a number of recommendations for the evaluation of systems that cater for content-and-structure queries.

Video and XML retrieval test collections call for evaluation metrics that do not require a predefined retrieval unit. The use of traditional recall and precision metrics is problematic due to issues caused by `overlap' between result and reference items. The paper proposes evaluation metrics derived from a user-effort oriented view of information retrieval to address these problems. It builds on the Expected Search Length metric of Cooper, revived by Dunlop for the Expected Search Duration metric. Our work extends these previous works by demonstrating how to handle systematically the overlap problems introduced when the assumption of a fixed, predefined retrieval unit is removed from the benchmark setting.

The Glasgow IR group has carried out both theoretical and empirical work, aimed at giving end users efficient and effective access to large collections of multimedia data.

Relevance feedback techniques are designed to automatically improve a system's representation of a query by using documents the user has marked as relevant. However, traditional relevance feedback models suffer from a number of limitations that restrict their potential in supporting information seeking. One of the major limitations of relevance feedback is that it does not incorporate behavioural aspects of information seeking - how and why users assess relevance. We propose that relevance feedback should be viewed as a process of explanation and demonstrate how this limitation of relevance feedback techniques can be overcome by a theory of relevance feedback based on abductive inference.

To increase retrieval effectiveness, information retrieval systems must offer better supports to users in their information seeking activities. To achieve this, one major concern is to obtain a better understanding of the nature of the interaction between a user and an information retrieval system. For this, we need a means to analyse the interaction in information retrieval, so as to compare the interaction processes within and across information retrieval systems. We present a framework for investigating the interaction between users and information retrieval systems. The framework is based on channel theory, a theory of information and its flow, which provides an explicit ontology that can be used to represent any aspect of the interaction process. The developed framework allows for the investigation of the interaction in information retrieval at the desired level of abstraction.We use the framework to investigate the interaction in relevance feedback and standard web search.