Conversational search addresses users’ information needs through multi-turn and context-aware interactions. Given that user queries are often ambiguous, the use of clarifying questions can effectively reduce uncertainty and enable a mixed-initiative conversational system. However, current datasets for clarifying questions remain limited in the following three aspects: (1) underrepresented multi-turn conversational data, (2) limited diversity, and (3) heavily reliance on crowdsourcing, thereby suffering from limitations such as high annotation cost. To address these issues, we propose a large language model (LLM)-based three-stage framework that relies on an existing community question answering dataset. It encompasses: (1) extracting essential information from the initial user query with the relevant contextual information, (2) generating clarifying questions paired with corresponding answers, and (3) refining conversations to ensure coherence and a natural conversational flow. We assess our multi-stage method against a baseline that directly prompts LLMs to generate conversations in a single-step process, evaluating on an answer retrieval task using recall, precision, normalized discounted cumulative gain and mean average precision. Results show that our three-stage generation approach consistently outperforms the baseline particularly in recall, while also achieving competitive results across other metrics. Human and automatic evaluations further indicate the high quality of generated conversations and fine-tuning on them improves retrieval performance, highlighting the pipeline’s potential.

Large Language Models (LLMs) have shown impressive zero-shot performance across a variety of Natural Language Processing tasks, including document re-ranking. However, their effectiveness degrades on unseen tasks and domains, largely due to shifts in vocabulary and word distributions. In this paper, we investigate Task Arithmetic, a technique that combines the weights of LLMs pre-trained on different tasks or domains via simple mathematical operations, such as addition or subtraction, to adapt retrieval models without requiring additional fine-tuning. Our method is able to synthesize diverse tasks and domain knowledge into a single model, enabling effective zero-shot adaptation in different retrieval contexts. Extensive experiments on publicly available scientific, biomedical, and multilingual datasets show that our method improves state-of-the-art re-ranking performance by up to 18% in NDCG@10 and 15% in P@10. In addition to these empirical gains, our analysis provides insights into the strengths and limitations of Task Arithmetic as a practical strategy for zero-shot learning and model adaptation. We make our code publicly available at https://github.com/DetectiveMB/Task-Arithmetic-for-ZS-IR.

Academic Search is a search task aimed to manage and retrieve scientific documents like journal articles and conference papers. Personalization in this context meets individual researchers’ needs by leveraging, through user profiles, the user related information (e.g. documents authored by a researcher), to improve search effectiveness and to reduce the information overload. While citation graphs are a valuable means to support the outcome of recommender systems, their use in personalized academic search (with, e.g. nodes as papers and edges as citations) is still under-explored. Existing personalized models for academic search often struggle to fully capture users’ academic interests. To address this, we propose a two-step approach: first, training a neural language model for retrieval, then converting the academic graph into a knowledge graph and embedding it into a shared semantic space with the language model using translational embedding techniques. This allows user models to capture both explicit relationships and hidden structures in citation graphs and paper content. We evaluate our approach in four academic search domains, outperforming traditional graph-based and personalized models in three out of four, with up to a 10% improvement in MAP@100 over the second-best model. This highlights the potential of knowledge graph-based user models to enhance retrieval effectiveness.

Abstract In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token into the input of the cross-encoder re-ranker. It was shown in prior work that interpolation between the relevance score of lexical and Bidirectional Encoder Representations from Transformers (BERT) based re-rankers may not consistently result in higher effectiveness. Our idea is motivated by the finding that BERT models can capture numeric information. We compare several representations of the Best Match 25 (BM25) and Dense Passage Retrieval (DPR) scores and inject them as text in the input of four different cross-encoders. Since knowledge distillation, i.e., teacher-student training, proved to be highly effective for cross-encoder re-rankers, we additionally analyze the effect of injecting the relevance score into the student model while training the model by three larger teacher models. Evaluation on the MSMARCO Passage collection and the TREC DL collections shows that the proposed method significantly improves over all cross-encoder re-rankers as well as the common interpolation methods. We show that the improvement is consistent for all query types. We also find an improvement in exact matching capabilities over both the first-stage rankers and the cross-encoders. Our findings indicate that cross-encoder re-rankers can efficiently be improved without additional computational burden or extra steps in the pipeline by adding the output of the first-stage ranker to the model input. This effect is robust for different models and query types.

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a Re-Ranker based on the novel Proportional Relevance Score (RPRS) to compute the relevance score between a query and the top- k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient, since all documents can be pre-processed, embedded, and indexed before query time that gives our re-ranker the advantage of having a complexity of O(N) , where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.

Personalized Query Expansion, the task of expanding queries with additional terms extracted from the user-related vocabulary, is a well-known solution to improve the retrieval performance of a system w.r.t. short queries. Recent approaches rely on word embeddings to select expansion terms from user-related texts. Although promising results have been delivered with former word embedding techniques, we argue that these methods are not suited for contextual word embeddings, which produce a unique vector representation for each term occurrence. In this article, we propose a Personalized Query Expansion method designed to solve the issues arising from the use of contextual word embeddings with the current Personalized Query Expansion approaches based on word embeddings. Specifically, we employ a clustering-based procedure to identify the terms that better represent the user interests and to improve the diversity of those selected for expansion, achieving improvements of up to 4% w.r.t. the best-performing baseline in terms of MAP@100. Moreover, our approach outperforms previous ones in terms of efficiency, allowing us to achieve sub-millisecond expansion times even in data-rich scenarios. Finally, we introduce a novel metric to evaluate the expansion terms’ diversity and empirically show the unsuitability of previous approaches based on word embeddings when employed along with contextual word embeddings, which cause the selection of semantically overlapping expansion terms.

Personalization in Information Retrieval has been a hot topic in both academia and industry for the past two decades. However, there is still a lack of high-quality standard benchmark datasets for conducting offline comparative evaluations in this context. To mitigate this problem, in the past few years, approaches to derive synthetic datasets suited for evaluating Personalized Search models have been proposed. In this paper, we put forward a novel evaluation benchmark for Personalized Search with more than 18 million documents and 1.9 million queries across four domains. We present a detailed description of the benchmark construction procedure, highlighting its characteristics and challenges. We provide baseline performance including pre-trained neural models, opening room for the evaluation of personalized approaches, as well as domain adaptation and transfer learning scenarios. We make both datasets and models available for future research.

Searching in a domain-specific corpus of structured documents (e.g., e-commerce, media streaming services, job-seeking platforms) is often managed as a traditional retrieval task or through faceted search. Semantic Query Labeling --- the task of locating the constituent parts of a query and assigning domain-specific predefined semantic labels to each of them --- allows leveraging the structure of documents during retrieval while leaving unaltered the keyword-based query formulation. Due to both the lack of a publicly available dataset and the high cost of producing one, there have been few published works in this regard. In this paper, basing on the assumption that a corpus already contains the information the users search, we propose a method for the automatic generation of semantically labeled queries and show that a semantic tagger --- based on BERT, gazetteers-based features, and Conditional Random Fields --- trained on our synthetic queries achieves results comparable to those obtained by the same model trained on real-world data. We also provide a large dataset of manually annotated queries in the movie domain suitable for studying Semantic Query Labeling. We hope that the public availability of this dataset will stimulate future research in this area.

The Third WEPIR 2020 workshop builds on the success of the first two WEPIR meetings held at CHIIR 2018 and CHIIR 2019. WEPIR 2020 again brings together researchers from different backgrounds interested in continuing to explore and advance the evaluation of personalisation in information retrieval. Similar to the first two workshops, WEPIR 2020 has a strong emphasis on active participation by workshop attendees. This was very successfully achieved in the first two workshops by the use of workshop breakout groups exploring topics related to personalisation and information retrieval, and the evaluation of personalisation in information retrieval in general, with subsequent report back to the workshop as a whole. However, a key difference for WEPIR 2020 is that while the first two workshops focused on developing and articulating principles and ideas relating general topics relating to these topics, identified as interesting and important by the attendees at the workshops, WEPIR 2020 focuses breakout discussion on a number of relevant specific use cases of the evaluation of personalisation in information retrieval. A use case is assigned to each breakout group with the plan being to have more than one group work on each use case. The task for each group is to identify specific relevant factors relating to the use case in terms of user activities, data to be collected, ethical issues, and evaluation metrics. Groups will make reports of their discussions to the assembled workshop in the final session with discussion of the alternative solutions relating to the same use case, and contrasting the issues raised by the different use cases. The overall goal of the workshop is to work towards developing a general set of principles and guidelines for addressing the evaluation of specific instances of the use of personalisation in information retrieval tasks. This is consistent with the activities and goals of the first two workshops, but represents a significant progression of the activities towards concrete outcomes of benefit to those exploring personalisation in search, the issues arising in its evaluation, and how researchers might go about tackling this in specific situations.

The second WEPIR 2019 workshop brings together researchers with different backgrounds interested in continuing to explore and advance the evaluation of personalisation in information retrieval. The workshop builds on the first WEPIR workshop held at CHIIR 2018, and will focus on further developing a common understanding of the challenges, requirements and practical limitations of meaningful evaluation of personalisation in information retrieval. In particular, the planned outcome of the workshop is to progress the work from WEPIR 2018 towards the development of concrete proposals for novel and innovative methodologies to support evaluation of personalised information retrieval from both the perspectives of the user experience in interactive search settings, and of user models for personalised information retrieval and their algorithmic incorporation in the search process.

The purpose of the WEPIR 2018 workshop is to bring together researchers from different backgrounds, interested in advancing the evaluation of personalisation in information retrieval. The workshop focus is on the development of a common understanding of the challenges, requirements and practical limitations of meaningful evaluation of personalisation in information retrieval. The planned outcome of the workshop is the proposal of methodologies to support evaluation of personalised information retrieval from both the perspectives of the user experience in interactive search settings, and of user models for personalised information retrieval and their algorithmic incorporation in the search process.

The Social Web represents nowadays the principal means to support and foster social interactions among people through Web 2.0 technologies. Individuals interact in virtual communities to pursue mutual interests or goals, by exchanging multiple kinds of contents (i.e., textual, acoustic, visual), the so-called User-Generated Content (UGC). In this context, the SeCredISData Special Session is especially devoted at discussing the implications that the analysis of big social data has in tackling open issues related to society from different perspectives. On one side, there is the need to push forward the research on emotion and sentiment, and the investigation of affective cognitive models and their possible integration into intelligent systems. On the other side, it is urgent to address the issue of on-line information credibility assessment, in an era where trusted intermediaries have disappeared and people must rely only on their cognitive capacities to judge information. The Special Session is therefore aimed at promoting the development of models and applications able to tackle these issues.

With "human centric data management", we denote all kind of practical and theoretical developments that contribute to the improvement of data management for human users, such that it becomes better to understand, easier to handle, and more natural to communicate with.The popularity of digital applications, social media and multimedia created a shift towards "big data" that are characterized by huge data volumes, a large variety of data formats, fast data processing requirements, and veracity problems.The more data we have at our disposal, the more applications arise, but also the more sophisticated these applications become.Along with these technological developments comes the awareness that there is a growing need for human centric data management tools.Indeed, perfect data sets are rare and data imperfections propagate to imperfect data processing solutions.Humans communicate in natural language and cope with imperfect information in their everyday behavior, whereas conventional data management assumes that data are perfect and data manipulation is based on a bivalent Boolean logic.Computational intelligence techniques, more specifically soft computing and fuzzy set theory, offer the tools for bridging the gap between the way humans behave and communicate and the way conventional data management tools work.This is especially the case because they allow to generalize bivalent Boolean logic into multivalued fuzzy logic and offer sound foundations for uncertainty modeling that are less stringent, but broader applicable, than conventional probability theory.This special issue is an initiative of the working group on "Soft Computing in Database Management and Information Retrieval" of the European Society for

Nowadays, review sites are more and more confronted with the spread of misinformation, i.e., opinion spam, which aims at promoting or damaging some target businesses, by misleading either human readers, or automated opinion mining and sentiment analysis systems. For this reason, in the last years, several data-driven approaches have been proposed to assess the credibility of user-generated content diffused through social media in the form of on-line reviews. Distinct approaches often consider different subsets of characteristics, i.e., features, connected to both reviews and reviewers, as well as to the network structure linking distinct entities on the review-site in exam. This article aims at providing an analysis of the main review- and reviewer-centric features that have been proposed up to now in the literature to detect fake reviews, in particular from those approaches that employ supervised machine learning techniques. These solutions provide in general better results with respect to purely unsupervised approaches, which are often based on graph-based methods that consider relational ties in review sites. Furthermore, this work proposes and evaluates some additional new features that can be suitable to classify genuine and fake reviews. For this purpose, a supervised classifier based on Random Forests have been implemented, by considering both well-known and new features, and a large-scale labeled dataset from which all these features have been extracted. The good results obtained show the effectiveness of new features to detect in particular singleton fake reviews, and in general the utility of this study.

When looking for recently published scientific papers, a researcher usually focuses on the topics related to her/his scientific interests. The task of a recommender system is to provide a list of unseen papers that match these topics. The core idea of this paper is to leverage the latent topics of interest in the publications of the researchers, and to take advantage of the social structure of the researchers (relations among researchers in the same field) as reliable sources of knowledge to improve the recommendation effectiveness. In particular, we introduce a hybrid approach to the task of scientific papers recommendation, which combines content analysis based on probabilistic topic modeling and ideas from collaborative filtering based on a relevance-based language model. We conducted an experimental study on DBLP, which demonstrates that our approach is promising.

In this paper the task of Information Foraging (IF) is considered as a useful paradigm to address Exploratory Search. In the context of IF, a Web navigation strategy is introduced and formalized, and a multi-agent based model is proposed to exploit a collaborative approach to Information Foraging. A system based on this model has been developed, and its evaluations on the ACM and DBLP repositories are reported. Two datasets with different sizes were considered to show the effectiveness and the efficiency of the developed system. Furthermore, comparative evaluations were conducted in order to compare our approach with classical information access approaches. The results are promising and show the ability of the proposed Web Information Foraging system to find relevant Web pages in a very short time.

The Social Web supports and fosters social interactions by means of different social media, which allow the spread of the so called User-Generated Content (UGC). In this context, characterized by the absence of trusted third parties that verify the reliability of the sources and the believability of the content generated, the issue of assessing the credibility of the information diffused by means of social media is receiving increasing attention. In the literature, this issue has been mainly tackled as a classification problem; information is categorized into genuine and fake, usually by implementing or applying classifiers that consider multiple kinds of features (mainly textual and non-textual) to be evaluated in terms of credibility.

This article presents an approach for the identification of potential new occupations, i.e., professions, not yet codified by the international standard taxonomy ISCO. This work is framed within the research activities of the WoLMIS project, developed by the University of Milano-Bicocca for the CEDEFOP European Agency, which classifies on-line job offers according to the ISCO taxonomy by using machine learning techniques.

Nowadays, User Generated Content is the main source of real time news and opinions on the world happenings. Social Media, which serves as an environment for the creation and spreading of User Generated Content, is, therefore, representative of our culture and constitutes a potential treasury of knowledge. In this paper we propose a fully automatic approach for modeling and tracking the information evolution in Social Media. In particular, we propose to model a Social Media stream as a text graph. A graph degeneracy technique is used to identify the temporal sequence of the core units of information streams represented by graphs. Furthermore, as the major novelty of this work, we propose a set of measures to track and evaluate the evolution of information in time. An experimental evaluation on the crawled datasets from one of the most popular Social Media platforms proves the validity and applicability of the proposed approach.

The Social Web is characterized by a massive diffusion of unfiltered content, directly generated by users via the spread of different social media platforms. In this context, a challenging issue is to assess the veracity of the information generated within the sites of online reviews. To address this issue, a common practice in the literature is to select and analyze some veracity features associated with users and their reviews, by mostly applying machine learning techniques, to provide a classification in genuine and deceptive reviews. In this paper, we do not focus on the feature selection and user behavior analysis issues, but we concentrate on the aggregation process with respect to each single veracity feature. In most of the approaches based on machine learning techniques, the contribution of each feature in the classification process is not measurable by the user. For this reason, we propose a multicriteria decision making approach based both on the assessment of multiple criteria and the use of aggregation operators with the aim of obtaining a veracity score associated with each review. Based on this score, it is possible to detect fake reviews. The proposed model is evaluated on a Yelp data set by applying different aggregation schemes, and it is compared with well-known supervised machine learning techniques.

Relevance is a central notion in Information Retrieval, but it is considered to be a difficult concept to define. We analyse brain signals for the first 800 milliseconds (ms) of a relevance assessment process to answer the question "when relevance is happening in the brain?" with the belief that it will lead to better operational definitions of relevance. For this purpose, we devised a user study in which we captured the brain response of 20 participants. Using a 64-channel EEG device, we measured the electrophysiological activity of the brain while the subjects were in the phase of giving an explicit judgement about the relevance of presented images according to a given topic. Analyses were then performed over different time windows of the recorded EEG signals using repeated measures ANOVA. Data reveal significant variation between relevance and non-relevance within the EEG signals from the presentation of the image to 800 milliseconds afterwards. At an early stage these differences were located at frontal and posterior electrode sites. However, at later stages these differences were located in central, centro-parietal and centro-frontal areas.Our findings are an important step towards (i) a better understanding of the concept of relevance and (ii) a more effective implicit feedback systems.

The Internet of Things and the Web of Things have focused on context awareness as a central issue in defining complex autonomic systems that rely on various layers, including devices, communications and applications. The spread usage of mobile devices that allow users to generate and to access distributed data makes it extremely important to organize the forwarding and gathering of such data in a user centered way, which may support a targeted process of data analytics. Data science should strongly take into account the individual and her/his needs to look at data from a personal perspective. In this contribution an integrated view of context awareness is presented, with the several technological and scientific issues that it raises.

The result set from a search engine for any user's query may exhibit an inherent perspective due to issues with the search engine or issues with the underlying collection. This demonstration paper presents a system that allows users to specify at query time a perspective together with their query. The system then presents results from well-known search engines with a visualization of the results which allows the users to quickly surmise the presence of the perspective in the returned set.

XML is the most used language for structuring data and documents, besides being the de-facto standard for data exchange. Keyword based search has been implemented by the XQuery Full-Text language extension, allowing document fragments to be retrieved and ranked via keyword-based matching in the Information Retrieval style. In this demo the implementation of an XQuery extension allowing users to express their vague knowledge of the underlying XML structure is presented. The integration has been performed on top of the BaseX query engine; the work, as initially done by Panzeri at al. in IIR 2013 as a proof-of-concept has been further enhanced and extended.

Finding domain specific key terms/phrases from a given set of documents is a challenging task. A domain may be defined as an area of interest over a collection of documents which may not be explicitly defined but implicitly observable in those documents. When considering a collection of documents related to academic research, examples of key terms/phrases may be Information Retrieval", "Marine Biology", etc. In this paper a technique for extracting important key terms/phrases in a considered topical domain is proposed using external evidence from the titles of Wikipedia articles and the Wikipedia category graph. We performed some experiments over the document collection of Web sites of different post-graduate schools. Our preliminary evaluations show promising results for the detection of domain specific key terms/phrases from the given set of domain focused Web pages.

Abstract: In recent years there has been a great deal of research about personalization in information access. The main issue is to improve the quality of search by producing user- tailored results related to specific user needs. In this context two key research problems concerns how to model user preferences, and how to exploit them in effective personalisation processes. This talk will address the above problems, and will discuss some important issues related to their possible solutions. The talk will also point out some research directions worth to be explored.

In this paper an original soft hierarchical Fuzzy Clustering algorithm is proposed, named Hierarchical Hyper-spherical Divisive Fuzzy C-Means (H2D-FCM), with the following characteristics: it generates a “soft” hierarchy in which a document can belong to several child clusters of a node, and the clusters in the same hierarchical level are more specific (general) than the clusters in the upper (lower) level. The proposed algorithm is a divisive algorithm based on a modified bisective K-Means, applying a modified probabilistic Fuzzy C Means algorithm to divide each node into child-nodes. The algorithm determines the proper number of cluster to generate at the first level based on an entropy measure and decides if a node can be further split based on a “density” measure. The paper presents the algorithm and its evaluations on two standard collections.

This work presents a flexible XML selection language, FleXPath which allows the formulation of flexible constraints on both structure and content of XML documents. Some experimental results, obtained with a preliminary prototype, are described in order to show that the idea promises good results.

In this paper, we model the evaluation of soft conditional preferences in flexibly querying fuzzy databases. We assume that soft conditional preferences are expressed in the form “If C then Q1 is better than Q2,” where C is the primary condition, and Q1, Q2 are the conditions with preferences. They are fuzzy predicates, which represent soft constraints admitting satisfaction degrees. The satisfaction degree of C tunes the preference of Q1 over Q2, so that as it increases also the preference of Q1 increases with respect to Q2. When C is not satisfied at all there is no preference between Q1 and Q2. The basic idea of the proposed model is to compute the preference degree of Q1 with respect to Q2 depending on the degree of satisfaction of C, and to use this value to modify the evaluation function of the soft conditions Q1 and Q2. This way we fuse in a single step the evaluations of both the selection conditions and their preference, which are the two subsequent phases necessary for evaluating queries with preferences in fuzzy databases. Specifically, the preference degree is used to relax the soft constraint imposed by the evaluation function of the most preferred condition Q1 as well as to restrict the evaluation function of the less preferred condition Q2. The more a soft condition is preferred, the more its evaluation function becomes tolerant to undersatisfaction; similarly, the less a condition is preferred the more its evaluation function is restricted so as to make more difficult its satisfaction. © 2008 Wiley Periodicals, Inc.

In this paper we present a novel filtering system, based on a new model which reshapes the aims of content-based filtering. The filtering system has been developed within the EC project PENG, aimed at providing news professionals, such as journalists, with a system supporting both filtering and retrieval capabilities. In particular, we suggest that in tackling the problem of information overload, it is necessary for filtering systems to take into account multiple aspects of incoming documents in order to estimate their relevance to a user's profile, and in order to help users better understand documents, as distinct from solely attempting to either select relevant material from a stream, or block inappropriate material. Aiming to so this, a filtering model based on multiple criteria has been defined, based on the ideas gleamed in the project requirements stage. The filtering model is briefly described in this paper.

A flexible model for evaluating soft query with unequal preferences in fuzzy databases is proposed. We assume that conditions with unequal preferences have an exclusive meaning like in the request “find a holiday accommodation such that big apartments are preferred to high rating hotels.” In this case it is assumed that the aggregator of the soft conditions is an implicit OR. Conversely, conditions with unequal importance have an inclusive meaning, like in the query “find a house to rent that is cheap (most important), big (important), new (fairly important).” In this case the implicit aggregator is an AND. What we propose in this article is to model preferences as modifiers of the semantics of the evaluation function of the conditions. Because the soft conditions are aggregated by an OR, the more a soft condition is preferred, the more its evaluation function tolerates a greater undersatisfaction of the soft condition. The proposed approach is formalized by considering two alternative semantics of the evaluation function: the first semantics defines the evaluation function by means of a generalized fuzzy inclusion measure, and the second one as a generalized similarity measure. These functions are parameterized so that their modification is simply achieved by tuning the functions' parameters. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 665–689, 2007.

Abstract The World Wide Web is a popular and interactive medium used to collect, disseminate, and access an increasingly huge amount of information, which constitutes the mainstay of the so‐called information and knowledge society. Because of its spectacular growth, related to both Web resources (pages, sites, and services) and number of users, the Web is nowadays the main information repository and provides some automatic systems for locating, accessing, and retrieving information. However, an open and crucial question remains: how to provide fast and effective retrieval of the information relevant to specific users' needs. This is a very hard and complex task, since it is pervaded with subjectivity, vagueness, and uncertainty. The expression soft computing refers to techniques and methodologies that work synergistically with the aim of providing flexible information processing tolerant of imprecision, vagueness, partial truth, and approximation. So, soft computing represents a good candidate to design effective systems for information access and retrieval on the Web. One of the most representative tools of soft computing is fuzzy set theory. This special topic section collects research articles witnessing some recent advances in improving the processes of information access and retrieval on the Web by using soft computing tools, and in particular, by using fuzzy sets and/or integrating them with other soft computing tools. In this introductory article, we first review the problem of Web retrieval and the concept of soft computing technology. We then briefly introduce the articles in this section and conclude by highlighting some future research directions that could benefit from the use of soft computing technologies.

Abstract An evaluation methodology based on fuzzy computing with words aimed at measuring the information quality of Web sites containing documents is presented. This methodology is qualitative and user oriented because it generates linguistic recommendations on the information quality of the content‐based Web sites based on users' perceptions. It is composed of two main components, an evaluation scheme to analyze the information quality of Web sites and a measurement method to generate the linguistic recommendations. The evaluation scheme is based on both technical criteria related to the Web site structure and criteria related to the content of information on the Web sites. It is user driven because the chosen criteria are easily understandable by the users, in such a way that Web visitors can assess them by means of linguistic evaluation judgments. The measurement method is user centered because it generates linguistic recommendations of the Web sites based on the visitors' linguistic evaluation judgments. To combine the linguistic evaluation judgments we introduce two new majority guided linguistic aggregation operators, the Majority guided Linguistic Induced Ordered Weighted Averaging (MLIOWA) and weighted MLIOWA operators, which generate the linguistic recommendations according to the majority of the evaluation judgments provided by different visitors. The use of this methodology could improve tasks such as information filtering and evaluation on the World Wide Web.

In this article, the idea of user preference playing a role in systems for information access is analyzed. In particular, two main categories of systems that provide access to information were considered: systems for the retrieval of stored information items [i.e., information retrieval systems (IRSs) and database management systems (DBMSs)] and systems that offer a support to product brokering for online shopping in e-commerce. One of the common characteristics of such systems is that they constitute for a user a decision aid for identifying the preferred information items within a huge collection. In this study, the synergy between decision theory and some techniques for information access is outlined, aiming at stimulating the definition of new methods that enhance the existing systems. © 2003 Wiley Periodicals, Inc.

In this paper, the definition of graph-based operations to select and browse a fuzzy object oriented database which manages both crisp and fuzzy information is proposed. The underlying data model is a fuzzy graph-based model (FOOD), previously defined by Bordogna et al., within fuzzy set theory and possibility theory. The evaluation mechanism of the graph-based operations is formalized in terms of graph transformations and fuzzy pattern matching. © 2001 John Wiley & Sons, Inc.

In this paper, we focus on the web-shopping activity and on ways to improve the quality of the information available to consumers. We describe a tool, called a product space map, for the presentation of information about a product category which can help consumers in making purchasing decisions. Using this tool we first provide a clustering or segmentation of a product line, that is, 27-inch televisions, into price categories such as low end, moderate and high end. Once having this partitioning we then use the idea of linguistic summaries to describe the properties of each category with respect to relevant features. An example of such a summary is “Most TV's in the high price category provide extremely high resolution.” With the aid of such information it becomes much easier for consumers to understand the product line, see what they are getting for their money, and more easily and confidently locate products that are of particular value for the money. Considerable use is made of fuzzy set technology to provide the ability to describe the information in a way, using linguistic expressions, that is particularly consumer friendly. © 2001 John Wiley & Sons, Inc.

In this paper a flexible query language for expressing soft selection conditions on structured documents is presented and formalized within fuzzy set theory. Documents are represented as entities structured into logical sections in which the index terms play a distinct role. Users can indicate the preferred sections of documents, i.e., those which they estimate bearing the most interesting information, as well as quantify the number of sections which determine the global potential interest of the documents. A linguistic quantifier that specifies the approximate number of the sections in which the query terms should appear in the relevant documents expresses this last information. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

In this contribution an interpretation of linguistic qualifiers of uncertainty is proposed in the context of fuzzy databases; these qualifiers are defined in the framework of possibility theory to express incomplete knowledge on the represented world. The uncertain and vague information represented in a fuzzy database is formalized based on the notion of prioritized constraints with safeguard. © 2000 John Wiley & Sons, Inc.

In this paper, a fuzzy Object-Oriented Data model (FOOD) is defined based on the extension of a Graph-based Object model (D. Lucarella and A. Zanzi “A graph-oriented data model,” in Database and Expert Systems Applications, R. Wagner and H. Toma, Eds., Springer-Verlag, Berlin, 1996, pp. 197–206), in order to manage both crisp and imperfect information. These capabilities are requisites of many current applications dealing with data of different nature and with complex interrelationships. The model is based on a visual paradigm which supports both the representation of the data semantics and the direct browsing of the information. In the extended model both the database scheme and instances are represented as directed labeled graphs in which the fuzzy and uncertain information has its own representation. ©1999 John Wiley & Sons, Inc.

Information retrieval (IR) can be regarded as a natural instance of multicriteria decision making (MCDM). Queries are formulated as selection criteria aggregated by means of appropriate operators. Retrieval is then performed as a MCDM process by evaluating the degrees of satisfaction of the criteria by each document, and then aggregating them. Another decisional instance in IR concerns the problem of improving retrieval performance by taking into account user indications on documents relevance. Relevance feedback mechanisms exploit user-system interaction in order to improve retrieval results by means of an iterative process of query refinement. In this process the main decisional issue is that of finding new concepts (terms) with which to expand–modify the initial query so that it better reflects the user's information needs. In this paper we introduce a relevance feedback mechanism based on a dynamical consensus model originally proposed in the framework of group decision making. In the relevance feedback context the consensual interaction highlights associations among the most significant terms in the relevant retrieved documents selected by the user. The resulting associative structure can then be used to expand the original query by including new terms which result strongly associated with those in the query. ©1999 John Wiley & Sons, Inc.

A “softening” of the hard Boolean scheme for information retrieval is presented. In this approach, information retrieval is seen as a multicriteria decision-making activity in which the criteria to be satisfied by the potential solutions, i.e., the archived documents, are the requirements expressed in the query. the retrieval function is then an overall decision function evaluating the degree to which each potential solution satisfies a query consisting of information requirements aggregated by operators. Linguistic quantifiers and a connector dealing with primary and optional criteria are defined and introduced in the query language in order to specify the aggregation criteria of the single query requirements. These criteria make it possible for users to express queries in a simple and self-explanatory manner. In particular, linguistic quantifiers are defined which capture the intrinsic vagueness of information needs. © 1995 John Wiley & Sons, Inc.

The generalization of Boolean Information Retrieval Systems (IRS) is still an open research field; in fact, though such systems are diffused on the market, they present some limitations; one of the main features lacking in these systems is the ability to deal with the “imprecision” and “subjectivity” characterizing retrieval activity. However, the replacement of such systems would be much more costly than their evolution through the incorporation of new features to enhance their efficiency and effectiveness. Previous efforts in this area have led to the introduction of numeric weights to improve both document representation and query language. By attaching a numeric weight to a term in a query, a user can provide a quantitative description of the “importance” of that term in the documents he or she is looking for. However, the use of weights requires a clear knowledge of their semantics for translating a fuzzy concept into a precise numeric value. Our acquaintance with these problems led us to define, starting from an existing weighted Boolean retrieval model, a linguistic extension, formalized within fuzzy set theory, in which numeric query weights are replaced by linguistic descriptors which specify the degree of importance of the terms. This fuzzy linguistic model is defined and an evaluation is made of its implementation on a Boolean IRS. © 1993 John Wiley & Sons, Inc.