Others Also Use: A Robust Recommender System for Scientific Libraries

Geyer-Schulz, Andreas; Neumann, Andreas; Thede, Anke

doi:10.1007/978-3-540-45175-4_12

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A framework could either be built from scratch, or be based on existing frameworks such as MyMediaLite, 33 LensKit, 34 Mahout, 35 Duine, 36 RecLab Core, 37 easyrec, 38 or Recommender101. 39 Finally, the community could benefit from considering research results from related disciplines. In particular, research in the area of user modeling and scientometrics appears promising, as well as research from the general recommender-systems community about aspects beyond accuracy.…”

Section: Discussionmentioning

confidence: 99%

Research-paper recommender systems: a literature survey

et al. 2015

View full text Add to dashboard Cite

In the last 16 years, more than 200 research articles were published about research-paper recommender systems. We reviewed these articles and present some descriptive statistics in this paper, as well as a discussion about the major advancements and shortcomings and an overview of the most common recommendation concepts and approaches. We found that more than half of the recommendation approaches applied content-based filtering (55 %). Collaborative filtering was applied by only 18 % of the reviewed approaches, and graph-based recommendations by 16 %. Other recommendation concepts included stereotyping, item-centric recommendations, and hybrid recommendations. The content-based filtering approaches mainly utilized papers that the users had authored, tagged, browsed, or downloaded. TF-IDF was the most frequently applied weighting scheme. In addition to simple terms, n-grams, topics, and citations were utilized to model users' information needs. Our review revealed some shortcomings of the current research. First, it remains unclear which recommendation concepts and approaches are the most promising. For instance, researchers reported different results on the performance of contentbased and collaborative filtering. Sometimes content-based filtering performed better than collaborative filtering and Linnaeus University, Kalmar, Sweden sometimes it performed worse. We identified three potential reasons for the ambiguity of the results. (A) Several evaluations had limitations. They were based on strongly pruned datasets, few participants in user studies, or did not use appropriate baselines. (B) Some authors provided little information about their algorithms, which makes it difficult to re-implement the approaches. Consequently, researchers use different implementations of the same recommendations approaches, which might lead to variations in the results. (C) We speculated that minor variations in datasets, algorithms, or user populations inevitably lead to strong variations in the performance of the approaches. Hence, finding the most promising approaches is a challenge. As a second limitation, we noted that many authors neglected to take into account factors other than accuracy, for example overall user satisfaction. In addition, most approaches (81 %) neglected the user-modeling process and did not infer information automatically but let users provide keywords, text snippets, or a single paper as input. Information on runtime was provided for 10 % of the approaches. Finally, few research papers had an impact on research-paper recommender systems in practice. We also identified a lack of authority and long-term research interest in the field: 73 % of the authors published no more than one paper on research-paper recommender systems, and there was little cooperation among different co-author groups. We concluded that several actions could improve the research landscape: developing a common evaluation framework, agreement on the information to include in research papers, a stronger focus on non-accuracy aspect...

show abstract

Section: Discussionmentioning

confidence: 99%

Research-paper recommender systems: a literature survey

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Most librarians would argue that the digital library requires selection of content by librarians and obtains its value from that selection (Wallace, 2004). Such models of selection can be implemented in purpose‐built digital libraries by putting URLs in library catalogs (Burke, Germain, & Van Ullen, 2003) or by implementing versions of “others also use” recommender systems (which first proved their popularity on the Web) in front of legacy library OPACs (Geyer‐Schulz, Neumann, & Thede, 2003). In any of these implementations, traditional questions about content acquisition still play a role and will continue to do so as long as the digital library is institutionally based (Miller, 2002), even though the toolsets employed in collection development may be quite different (Mitchell, 2005).…”

Section: Servicesmentioning

confidence: 99%

Digital libraries

Bearman¹

2007

Annual Review Info Sci & Tec

View full text Add to dashboard Cite

show abstract

“…Apart from governmental organisations, libraries might also develop policies about other third par-ties who might be interested in the data generated by -and about -users (Corrado, 2007). Some libraries try to resolve the trade-off between extra functionalities and better service versus protecting personal information by adding recommender functions to their online public access catalogue (OPAC), based on anonymised usage data (Geyer-Schulz, Neumann, & Thede, 2003;Mönnich & Spiering, 2008).…”

Section: Libraries Privacy and The Role Of The Cataloguementioning

confidence: 99%

Patterns of information – clustering books and readers in open access libraries

Snijder¹

2017

Preprint

View full text Add to dashboard Cite

Open access libraries operate in a continuum between two distinct organisation models: online retailers versus ‘traditional’ libraries. Online retailers such as Amazon.com are successful in recom-mending additional items that match the specific needs of their customers. The success rate of the recommendation depends on knowledge of the individual customer: more knowledge about persons leads to better suggestions. Thus, to optimally profit from the retailers’ offerings, the client must be prepared to share personal information, leading to the question of privacy.In contrast, protection of privacy is a core value for libraries. The question is how open access librar-ies can offer comparable services while retaining the readers’ privacy. A possible solution can be found in analysing the preferences of groups of like-minded people: communities. According to Lynch (2002), digital libraries are bad at identifying or predicting the communities that will use their collections. It is however our intention to explore the possibility to uncover sets of documents with a meaningful connection for groups of readers – the communities. The solution depends on examining patterns of usage, instead of storing information about individual readers. This paper will investigate the possibility to uncover the preferences of user groups within an open access digital library using social networking analysis techniques.

show abstract

Others Also Use: A Robust Recommender System for Scientific Libraries

Cited by 9 publications

References 17 publications

Research-paper recommender systems: a literature survey

Research-paper recommender systems: a literature survey

Digital libraries

Patterns of information – clustering books and readers in open access libraries

Contact Info

Product

Resources

About