Matrix Factorization Techniques for Recommender Systems

本文对国际科学计量学杂志《Ｓｃｉｅｎｔｏｍｅｔｒｉｃｓ》１９７９－１９９１年的研究论文内容、栏目、作者及国别和编委及国别作了计量分析，揭示出科学计量学研究的重点、活动的中心及发展趋势，说明了学科带头人在发展科学计量学这门新兴学科中的作用。

国际刊物《Scientometrics》文献计量研究

This paper presents a new map representing the structure of all of science, based on journal articles, including both the natural and social sciences. Similar to cartographic maps of our world, the map of science provides a bird's eye view of today's scientific landscape. It can be used to visually identify major areas of science, their size, similarity, and interconnectedness. In order to be useful, the map needs to be accurate on a local and on a global scale. While our recent work has focused on the former aspect, this paper summarizes results on how to achieve structural accuracy. Eight alternative measures of journal similarity were applied to a data set of 7,121 journals covering over 1 million documents in the combined Science Citation and Social Science Citation Indexes. For each journal similarity measure we generated two-dimensional spatial layouts using the force-directed graph layout tool, VxOrd. Next, mutual information values were calculated for each graph at different clustering levels to give a measure of structural accuracy for each map. The best co-citation and inter-citation maps according to local and structural accuracy were selected and are presented and characterized. These two maps are compared to establish robustness. The inter-citation map is more » then used to examine linkages between disciplines. Biochemistry appears as the most interdisciplinary discipline in science. « less

Mapping the backbone of science.

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 content-based and collaborative filtering. Sometimes content-based filtering performed better than collaborative filtering and 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 aspects and user modeling, a platform for researchers to exchange information, and an open-source framework that bundles the available recommendation approaches.

/pdf/research-paper-recommender-systems-a-literature-survey-3o8izjcp9m.pdf

Research-paper recommender systems: a literature survey

Please provide a short abstract of 100 to 250 words. The abstract should not contain any undefined abbreviations or unspecified references. Work planned but not completed should not appear in the abstract.

User Modeling and User-Adapted Interaction

State-of-the-Art Recommender Systems

In our article we compare downloads from ScienceDirect, citations from Scopus and readership data from the social reference management system Mendeley for articles from two information systems journals ("Journal of Strategic Information Systems" and "Information and Management") published between 2002 and 2011. Our study shows a medium to high correlation between downloads and citations (Spearman r = 0.77/0.76) and between downloads and readership data (Spearman r = 0.73/0.66). The correlation between readership data and citations, however, was only medium-sized (Spearman r = 0.51/0.59). These results suggest that there is at least "some" difference between the two usage measures and the citation impact of the analysed information systems articles. As expected, downloads and citations have different obsolescence characteristics. While the highest number of downloads are usually made in the publication year and immediately afterwards, it takes several years until the citation maximum is reached. Furthermore, there was a re-increase in the downloads in later years which might be an indication that citations also have an effect on downloads to some degree.

Comparison of downloads, citations and readership data for two information systems journals

Text mining and information retrieval in large collections of scientific literature require automated processing systems that analyse the documents’ content. However, the layout of scientific articles is highly varying across publishers, and common digital document formats are optimised for presentation, but lack structural information. To overcome these challenges, we have developed a processing pipeline that analyses the structure a PDF document using a number of unsupervised machine learning techniques and heuristics. Apart from the meta-data extraction, which we reused from previous work, our system uses only information available from the current document and does not require any pre-trained model. First, contiguous text blocks are extracted from the raw character stream. Next, we determine geometrical relations between these blocks, which, together with geometrical and font information, are then used categorize the blocks into different classes. Based on this resulting logical structure we finally extract the body text and the table of contents of a scientific article. We separately evaluate the individual stages of our pipeline on a number of different datasets and compare it with other document structure analysis approaches. We show that it outperforms a state-of-the-art system in terms of the quality of the extracted body text and table of contents. Our unsupervised approach could provide a basis for advanced digital library scenarios that involve diverse and dynamic corpora.

Unsupervised document structure analysis of digital scientific articles

An important aspect of the work of researchers as well as librarians is to manage collections of scientific literature. Social research networks, such as Mendeley and CiteULike, provide services that support this task. Meta-data plays an important role in providing services to retrieve and organise the articles. In such settings, meta-data is rarely explicitly provided, leading to the need for automatically extracting this valuable information. The TeamBeam algorithm analyses a scientific article and extracts structured meta-data, such as the title, journal name and abstract, as well as information about the article's authors (e.g. names, e-mail addresses, affiliations). The input of the algorithm is a set of blocks generated from the article text. A classification algorithm, which takes the sequence of the input into account, is then applied in two consecutive phases. In the evaluation of the algorithm, its performance is compared against two heuristics and three existing meta-data extraction systems. Three different data sets with varying characteristics are used to assess the quality of the extraction results. TeamBeam performs well under testing and compares favourably with existing approaches.

TeamBeam Meta-Data Extraction from Scientific Literature

Social reference management systems provide a wealth of information that can be used for the analysis of science. In this paper, we examine whether user library statistics can produce meaningful results with regards to science evaluation and knowledge domain visualization. We are conducting two empirical studies, using a sample of library data from Mendeley, the world's largest social reference management system. Based on the occurrence of references in users' libraries, we perform a large-scale impact factor analysis and an exploratory co-readership analysis. Our preliminary findings indicate that the analysis of user library statistics can produce accurate, timely, and content-rich results. We find that there is a significant relationship between the impact factor and the occurrence of references in libraries. Using a knowledge domain visualization based on co-occurrence measures, we are able to identify two areas of topics within the emerging field of technology-enhanced learning.

Kris Jack

Papers

State-of-the-Art Recommender Systems

Comparison of downloads, citations and readership data for two information systems journals

Unsupervised document structure analysis of digital scientific articles

TeamBeam Meta-Data Extraction from Scientific Literature

Harnessing user library statistics for research evaluation and knowledge domain visualization