@article{bates_design_1989, title = {The design of browsing and berrypicking techniques for the online search interface}, volume = {13}, issn = {0309-314X}, url = {http://www.emeraldinsight.com/doi/abs/10.1108/eb024320}, abstract = {First, a new model of searching in online and other information systems, called ‘berrypicking’, is discussed. This model, it is argued, is much closer to the real behavior of information searchers than the traditional model of information retrieval is, and, consequently, will guide our thinking better in the design of effective interfaces. Second, the research literature of manual information seeking behavior is drawn on for suggestions of capabilities that users might like to have in online systems. Third, based on the new model and the research on information seeking, suggestions are made for how new search capabilities could be incorporated into the design of search interfaces. Particular attention is given to the nature and types of browsing that can be facilitated.}, language = {en}, number = {5}, urldate = {2017-04-06}, journal = {Online Review}, author = {Bates, Marcia J.}, month = may, year = {1989}, pages = {407--424}, } @article{kuhlthau_inside_1991, title = {Inside the {Search} {Process}: {Information} {Seeking} from the {User}'s {Perspective}}, volume = {42}, issn = {0002-8231}, url = {http://search.proquest.com/docview/1301244250/citation/2FBBEAD901A4984PQ/1}, language = {en}, number = {5}, urldate = {2017-04-06}, journal = {Journal of the American Society for Information Science}, author = {Kuhlthau, Carol C.}, year = {1991}, } @article{ingwersen_ranganathan_1992, title = {Ranganathan in the {Perspective} of {Advanced} {Information} {Retrieval}}, volume = {42}, issn = {0024-2667}, url = {https://search.proquest.com/docview/1304366227?pq-origsite=gscholar}, language = {en}, number = {3}, urldate = {2018-03-20}, journal = {Libri}, author = {Ingwersen, Peter and Wormell, Irene}, year = {1992}, } @article{kuhlthau_principle_1993, title = {A principle of uncertainty for information seeking}, volume = {49}, issn = {0022-0418}, url = {http://www.emeraldinsight.com/doi/abs/10.1108/eb026918}, doi = {10.1108/eb026918}, language = {en}, number = {4}, urldate = {2017-04-06}, journal = {Journal of Documentation}, author = {Kuhlthau, Carol C.}, month = apr, year = {1993}, pages = {339--355}, } @article{spiteri_simplified_1998, title = {A simplified model for facet analysis: {Ranganathan} 101}, volume = {23}, issn = {1195-096X}, language = {en}, number = {1-2}, journal = {Canadian journal of information and library science}, author = {Spiteri, Louise}, year = {1998}, pages = {1--30}, } @article{pirolli_information_1999, title = {Information foraging}, volume = {106}, copyright = {(c) 2016 APA, all rights reserved}, issn = {1939-1471 0033-295X}, doi = {10.1037/0033-295X.106.4.643}, abstract = {Information foraging theory is an approach to understanding how strategies and technologies for information seeking, gathering, and consumption are adapted to the flux of information in the environment. The theory assumes that people, when possible, will modify their strategies or the structure of the environment to maximize their rate of gaining valuable information. The theory is developed by (a) adaptation (rational) analysis of information foraging problems and (b) a detailed process model (adaptive control of thought in information foraging [ACT-IF]). The adaptation analysis develops (a) information patch models, which deal with time allocation and information filtering and enrichment activities in environments in which information is encountered in clusters; (b) information scent models, which address the identification of information value from proximal cues; and (c) information diet models, which address decisions about the selection and pursuit of information items. ACT-IF is instantiated as a production system model of people interacting with complex information technology.}, language = {en}, number = {4}, journal = {Psychological Review}, author = {Pirolli, Peter and Card, Stuart}, year = {1999}, pages = {643--675}, } @article{wilson_models_1999, title = {Models in information behaviour research}, volume = {55}, issn = {0022-0418}, doi = {10.1108/EUM0000000007145}, abstract = {This paper presents an outline of models of information seeking and other aspects of information behaviour, showing the relationship between communication and information behaviour in general with information seeking and information searching in information retrieval systems. It is suggested that these models address issues at various levels of information behaviour and that they can be related by envisaging a ‘nesting’ of models. It is also suggested that, within both information seeking research and information searching research, alternative models address similar issues in related ways and that the models are complementary rather than conflicting. Finally, an alternative, problem-solving model is presented, which, it is suggested, provides a basis for relating the models in appropriate research strategies.}, language = {en}, number = {3}, journal = {Journal of Documentation}, author = {Wilson, T. D.}, year = {1999}, pages = {249--270}, } @article{broder_taxonomy_2002, title = {A {Taxonomy} of {Web} {Search}}, volume = {36}, issn = {0163-5840}, url = {http://doi.acm.org/10.1145/792550.792552}, doi = {10.1145/792550.792552}, abstract = {Classic IR (information retrieval) is inherently predicated on users searching for information, the so-called "information need". But the need behind a web search is often not informational -- it might be navigational (give me the url of the site I want to reach) or transactional (show me sites where I can perform a certain transaction, e.g. shop, download a file, or find a map). We explore this taxonomy of web searches and discuss how global search engines evolved to deal with web-specific needs.}, language = {en}, number = {2}, urldate = {2018-08-03}, journal = {SIGIR Forum}, author = {Broder, Andrei}, month = sep, year = {2002}, pages = {3--10}, } @misc{denton_how_2003, title = {How to {Make} a {Faceted} {Classification} and {Put} {It} {On} the {Web}}, url = {https://www.miskatonic.org/library/facet-web-howto.html}, language = {en}, urldate = {2016-08-16}, journal = {Miskatonic University Press}, author = {Denton, William}, year = {2003}, } @inproceedings{rose_understanding_2004, address = {New York, NY, USA}, series = {{WWW} '04}, title = {Understanding {User} {Goals} in {Web} {Search}}, isbn = {978-1-58113-844-3}, url = {http://doi.acm.org/10.1145/988672.988675}, doi = {10.1145/988672.988675}, abstract = {Previous work on understanding user web search behavior has focused on how people search and what they are searching for, but not why they are searching. In this paper, we describe a framework for understanding the underlying goals of user searches, and our experience in using the framework to manually classify queries from a web search engine. Our analysis suggests that so-called navigational" searches are less prevalent than generally believed while a previously unexplored "resource-seeking" goal may account for a large fraction of web searches. We also illustrate how this knowledge of user search goals might be used to improve future web search engines.}, language = {en}, urldate = {2018-03-28}, booktitle = {Proceedings of the 13th {International} {Conference} on {World} {Wide} {Web}}, publisher = {ACM}, author = {Rose, Daniel E. and Levinson, Danny}, year = {2004}, pages = {13--19}, } @article{broughton_need_2006, title = {The need for a faceted classification as the basis of all methods of information retrieval}, volume = {58}, issn = {0001-253X}, doi = {10.1108/00012530610648671}, abstract = {Purpose – The aim of this article is to estimate the impact of faceted classification and the faceted analytical method on the development of various information retrieval tools over the latter part of the twentieth and early twenty‐first centuries. Design/methodology/approach – The article presents an examination of various subject access tools intended for retrieval of both print and digital materials to determine whether they exhibit features of faceted systems. Some attention is paid to use of the faceted approach as a means of structuring information on commercial web sites. The secondary and research literature is also surveyed for commentary on and evaluation of facet analysis as a basis for the building of vocabulary and conceptual tools. Findings – The study finds that faceted systems are now very common, with a major increase in their use over the last 15 years. Most LIS subject indexing tools (classifications, subject heading lists and thesauri) now demonstrate features of facet analysis to a greater or lesser degree. A faceted approach is frequently taken to the presentation of product information on commercial web sites, and there is an independent strand of theory and documentation related to this application. There is some significant research on semi‐automatic indexing and retrieval (query expansion and query formulation) using facet analytical techniques. Originality/value – This article provides an overview of an important conceptual approach to information retrieval, and compares different understandings and applications of this methodology.}, language = {en}, number = {1/2}, journal = {Aslib Proceedings}, author = {Broughton, Vanda}, editor = {Dawson, Andy}, month = jan, year = {2006}, pages = {49--72}, } @article{godbold_beyond_2006, title = {Beyond {Information} {Seeking}: {Towards} a {General} {Model} of {Information} {Behaviour}}, volume = {11}, issn = {1368-1613}, shorttitle = {Beyond {Information} {Seeking}}, url = {https://eric.ed.gov/?id=EJ1104640}, abstract = {Introduction: The aim of the paper is to propose new models of information behaviour that extend the concept beyond simply information seeking to consider other modes of behaviour. The models chiefly explored are those of Wilson and Dervin. Argument: A shortcoming of some models of information behaviour is that they present a sequence of stages where it is evident that actual behaviour is not always sequential. In addition, information behaviour models tend to confine themselves to depictions of information seeking. Development: A model of "multi-directionality" is explored, to overcome the notion of sequential stages. Inspired by authors such as Chatman, Krikelas, and Savolainen, modes of information behaviour such as creating, destroying and avoiding information are included. Conclusion: New models of information behaviour are presented that replace the notion of "barriers" with the concept of "gap", as a means of integrating the views of Wilson and Dervin. The proposed models incorporate the notion of multi-directionality and identify ways in which an individual may navigate "gap" using modes of information behaviour beyond information seeking.}, language = {en}, number = {4}, urldate = {2019-01-25}, journal = {Information Research: An International Electronic Journal}, author = {Godbold, Natalya}, month = jul, year = {2006}, } @inproceedings{hearst_design_2006, title = {Design recommendations for hierarchical faceted search interfaces}, abstract = {This paper presents interface design recommendations for faceted navigation systems, based on 13 years of experience in experimenting with and evaluating such designs.}, language = {en}, booktitle = {{ACM} {SIGIR} workshop on faceted search}, publisher = {Seattle, WA}, author = {Hearst, Marti}, month = aug, year = {2006}, pages = {1--5}, } @article{broughton_building_2007, title = {Building a faceted classification for the humanities: principles and procedures}, volume = {63}, shorttitle = {Building a faceted classification for the humanities: principles and procedures}, abstract = {Purpose – This paper aims to provide an overview of principles and procedures involved in creating a faceted classification scheme for use in resource discovery in an online environment. Design/methodology/approach – Facet analysis provides an established rigorous methodology for the conceptual organization of a subject field, and the structuring of an associated classification or controlled vocabulary. This paper explains how that methodology was applied to the humanities in the FATKS project, where the objective was to explore the potential of facet analytical theory for creating a controlled vocabulary for the humanities, and to establish the requirements of a faceted classification appropriate to an online environment. A detailed faceted vocabulary was developed for two areas of the humanities within a broader facet framework for the whole of knowledge. Research issues included how to create a data model which made the faceted structure explicit and machine-readable and provided for its further development and use. Findings – In order to support easy facet combination in indexing, and facet searching and browsing on the interface, faceted classification requires a formalized data structure and an appropriate tool for its management. The conceptual framework of a faceted system proper can be applied satisfactorily to humanities, and fully integrated within a vocabulary management system. Research limitations/implications – The procedures described in this paper are concerned only with the structuring of the classification, and do not extend to indexing, retrieval and application issues. Practical implications – Many stakeholders in the domain of resource discovery consider developing their own classification system and supporting tools. The methods described in this paper may clarify the process of building a faceted classification and may provide some useful ideas with respect to the vocabulary maintenance tool. Originality/value – As far as the authors are aware there is no comparable research in this area.}, language = {en}, number = {5}, journal = {Journal of Documentation}, author = {Broughton, Vanda and Slavic, Aida}, year = {2007}, pages = {727--754}, } @article{vickery_faceted_2008, title = {Faceted {Classification} for the {Web}}, volume = {18}, issn = {1572-8390}, url = {http://dx.doi.org/10.1007/s10516-007-9025-9}, doi = {10.1007/s10516-007-9025-9}, abstract = {The article describes the nature of a faceted classification, and its application in document retrieval. The kinds of facet used are illustrated. Procedures are then discussed for identifying facets in a subject field, populating the facets with individual subject terms, arranging these in helpful sequences, using the scheme to classify documents, and searching the resultant classified index, with particular reference to Internet search.}, language = {en}, number = {2}, journal = {Axiomathes}, author = {Vickery, Brian}, year = {2008}, pages = {145--160}, } @inproceedings{gollapudi_axiomatic_2009, address = {New York, NY, USA}, series = {{WWW} '09}, title = {An {Axiomatic} {Approach} for {Result} {Diversification}}, isbn = {978-1-60558-487-4}, url = {http://doi.acm.org/10.1145/1526709.1526761}, doi = {10.1145/1526709.1526761}, abstract = {Understanding user intent is key to designing an effective ranking system in a search engine. In the absence of any explicit knowledge of user intent, search engines want to diversify results to improve user satisfaction. In such a setting, the probability ranking principle-based approach of presenting the most relevant results on top can be sub-optimal, and hence the search engine would like to trade-off relevance for diversity in the results. In analogy to prior work on ranking and clustering systems, we use the axiomatic approach to characterize and design diversification systems. We develop a set of natural axioms that a diversification system is expected to satisfy, and show that no diversification function can satisfy all the axioms simultaneously. We illustrate the use of the axiomatic framework by providing three example diversification objectives that satisfy different subsets of the axioms. We also uncover a rich link to the facility dispersion problem that results in algorithms for a number of diversification objectives. Finally, we propose an evaluation methodology to characterize the objectives and the underlying axioms. We conduct a large scale evaluation of our objectives based on two data sets: a data set derived from the Wikipedia disambiguation pages and a product database.}, language = {en}, urldate = {2019-01-27}, booktitle = {Proceedings of the 18th {International} {Conference} on {World} {Wide} {Web}}, publisher = {ACM}, author = {Gollapudi, Sreenivas and Sharma, Aneesh}, year = {2009}, pages = {381--390}, } @article{white_exploratory_2009, title = {Exploratory {Search}: {Beyond} the {Query}-{Response} {Paradigm}}, volume = {1}, issn = {1947-945X}, shorttitle = {Exploratory {Search}}, url = {https://www.morganclaypool.com/doi/abs/10.2200/S00174ED1V01Y200901ICR003}, doi = {10.2200/S00174ED1V01Y200901ICR003}, abstract = {As information becomes more ubiquitous and the demands that searchers have on search systems grow, there is a need to support search behaviors beyond simple lookup. Information seeking is the process or activity of attempting to obtain information in both human and technological contexts. Exploratory search describes an information-seeking problem context that is open-ended, persistent, and multifaceted, and information-seeking processes that are opportunistic, iterative, and multitactical. Exploratory searchers aim to solve complex problems and develop enhanced mental capacities. Exploratory search systems support this through symbiotic human-machine relationships that provide guidance in exploring unfamiliar information landscapes. Exploratory search has gained prominence in recent years. There is an increased interest from the information retrieval, information science, and human-computer interaction communities in moving beyond the traditional turn-taking interaction model supported by major Web search engines, and toward support for human intelligence amplification and information use. In this lecture, we introduce exploratory search, relate it to relevant extant research, outline the features of exploratory search systems, discuss the evaluation of these systems, and suggest some future directions for supporting exploratory search. Exploratory search is a new frontier in the search domain and is becoming increasingly important in shaping our future world.}, language = {en}, number = {1}, urldate = {2018-05-27}, journal = {Synthesis Lectures on Information Concepts, Retrieval, and Services}, author = {White, Ryen W. and Roth, Resa A.}, month = jan, year = {2009}, pages = {1--98}, } @article{radlinski_redundancy_2009, title = {Redundancy, diversity and interdependent document relevance}, volume = {43}, issn = {0163-5840}, url = {http://dl.acm.org/citation.cfm?id=1670564.1670572}, doi = {10.1145/1670564.1670572}, abstract = {The goal of the Redundancy, Diversity, and Interdependent Document Relevance workshop was to explore how ranking, performance assessment and learning to rank can move beyond the assumption that the relevance of a document is independent of other documents. In particular, the workshop focussed on three themes: the effect of redundancy on information retrieval utility (for example, minimizing the wasted effort of users who must skip redundant information), the role of diversity (for example, for mitigating the risk of misinterpreting ambiguous queries), and algorithms for set-level optimization (where the quality of a set of retrieved documents is not simply the sum of its parts). This workshop built directly upon the Beyond Binary Relevance: Preferences, Diversity and Set-Level Judgments workshop at SIGIR 2008 [3], shifting focus to address the questions left open by the discussions and results from that workshop. As such, it was the first workshop to explicitly focus on the related research challenges of redundancy, diversity, and interdependent relevance – all of which require novel performance measures, learning methods, and evaluation techniques. The workshop program committee consisted of 15 researchers from academia and industry, with experience in IR evaluation, machine learning, and IR algorithmic design. Over 40 people attended the workshop. This report aims to summarize the workshop, and also to systematize common themes and key concepts so as to encourage research in the three workshop themes. It contains our attempt to summarize and organize the topics that came up in presentations as well as in discussions, pulling out common elements. Many audience members contributed, yet due to the free-flowing discussion, attributing all the observations to particular audience members is unfortunately impossible. Not all audience members would necessarily agree with the views presented, but we do attempt to present a consensus view as far as possible.}, language = {en}, number = {2}, urldate = {2019-01-27}, journal = {ACM SIGIR Forum}, author = {Radlinski, Filip and Bennett, Paul N. and Carterette, Ben and Joachims, Thorsten}, month = dec, year = {2009}, pages = {46--52}, } @article{la_barre_facet_2010, title = {Facet analysis}, volume = {44}, issn = {1550-8382}, url = {http://onlinelibrary.wiley.com/doi/10.1002/aris.2010.1440440113/abstract}, language = {en}, number = {1}, urldate = {2017-01-27}, journal = {Annual Review of Information Science and Technology}, author = {La Barre, Kathryn}, month = jan, year = {2010}, pages = {243--284}, } @article{hjorland_foundation_2010, title = {The foundation of the concept of relevance}, volume = {61}, copyright = {© 2009 ASIS\&T}, issn = {1532-2890}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/asi.21261}, doi = {10.1002/asi.21261}, abstract = {In 1975 Tefko Saracevic declared “the subject knowledge view” to be the most fundamental perspective of relevance. This paper examines the assumptions in different views of relevance, including “the system's view” and “the user's view” and offers a reinterpretation of these views. The paper finds that what was regarded as the most fundamental view by Saracevic in 1975 has not since been considered (with very few exceptions). Other views, which are based on less fruitful assumptions, have dominated the discourse on relevance in information retrieval and information science. Many authors have reexamined the concept of relevance in information science, but have neglected the subject knowledge view, hence basic theoretical assumptions seem not to have been properly addressed. It is as urgent now as it was in 1975 seriously to consider “the subject knowledge view” of relevance (which may also be termed “the epistemological view”). The concept of relevance, like other basic concepts, is influenced by overall approaches to information science, such as the cognitive view and the domain-analytic view. There is today a trend toward a social paradigm for information science. This paper offers an understanding of relevance from such a social point of view.}, language = {en}, number = {2}, urldate = {2018-04-25}, journal = {Journal of the American Society for Information Science and Technology}, author = {Hjørland, Birger}, month = feb, year = {2010}, pages = {217--237}, } @article{broughton_faceted_2013, title = {Faceted classification as a general theory for knowledge organization}, volume = {50}, abstract = {The Classification Research Group manifesto of 1955, 'Faceted classification as the basis of all information retrieval', has been at least in part achieved, and there is much evidence of faceted classification influencing a whole range of modern information retrieval tools. This paper examines the theory underlying faceted classification, how and why it has been taken up so widely, and what benefits it brings to the activity of knowledge organization. The role of facet analysis as a general research tool is also considered, and how it compares with other content analysis tools as a means of modelling subject domains.}, language = {en}, number = {6}, journal = {SRELS Journal of Information Management}, author = {Broughton, Vanda}, year = {2013}, pages = {735--750}, } @article{hjorland_facet_2013, title = {Facet analysis: {The} logical approach to knowledge organization}, volume = {49}, issn = {0306-4573}, url = {http://www.sciencedirect.com/science/article/pii/S0306457312001203}, doi = {10.1016/j.ipm.2012.10.001}, abstract = {The facet-analytic paradigm is probably the most distinct approach to knowledge organization within Library and Information Science, and in many ways it has dominated what has be termed “modern classification theory”. It was mainly developed by S.R. Ranganathan and the British Classification Research Group, but it is mostly based on principles of logical division developed more than two millennia ago. Colon Classification (CC) and Bliss 2 (BC2) are among the most important systems developed on this theoretical basis, but it has also influenced the development of other systems, such as the Dewey Decimal Classification (DDC) and is also applied in many websites. It still has a strong position in the field and it is the most explicit and “pure” theoretical approach to knowledge organization (KO) (but it is not by implication necessarily also the most important one). The strength of this approach is its logical principles and the way it provides structures in knowledge organization systems (KOS). The main weaknesses are (1) its lack of empirical basis and (2) its speculative ordering of knowledge without basis in the development or influence of theories and socio-historical studies. It seems to be based on the problematic assumption that relations between concepts are a priori and not established by the development of models, theories and laws.}, language = {en}, number = {2}, journal = {Information Processing \& Management}, author = {Hjørland, Birger}, month = mar, year = {2013}, pages = {545--557}, } @article{godert_ontology-based_2016, title = {An ontology-based model for indexing and retrieval}, volume = {67}, copyright = {© 2015 ASIS\&T}, issn = {2330-1643}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/asi.23420}, doi = {10.1002/asi.23420}, abstract = {The presented ontology-based model for indexing and retrieval combines the methods and experiences of traditional indexing languages with their cognitively interpreted entities and relationships with the strengths and possibilities of formal knowledge representation. The core component of the model uses inferences along the paths of typed relations between the entities of a knowledge representation for enabling the determination of result sets in the context of retrieval processes. A proposal for a general, but condensed, inventory of typed relations is given. The entities are arranged in aspect-oriented facets to ensure a consistent hierarchical structure. The possible consequences for indexing and retrieval are discussed.}, language = {en}, number = {3}, urldate = {2019-01-25}, journal = {Journal of the Association for Information Science and Technology}, author = {Gödert, Winfried}, year = {2016}, pages = {594--609}, } @article{hudon_introduction._2017, title = {Introduction. {La} classification à facettes revisitée. {De} la théorie à la pratique}, volume = {13}, issn = {1622-1494}, url = {http://www.cairn.info/resume.php?ID_ARTICLE=LCN_131_0009}, language = {fr}, number = {1}, urldate = {2017-04-13}, journal = {Les Cahiers du numérique}, author = {Hudon, Michèle and Mustafa El Hadi, Widad}, month = apr, year = {2017}, pages = {9--24}, }