@inproceedings{karypis2001evaluation, abstract = {The explosive growth of the world-wide-web and the emergence of e-commerce has led to the development of recommender systems---a personalized information filtering technology used to identify a set of N items that will be of interest to a certain user. User-based Collaborative filtering is the most successful technology for building recommender systems to date, and is extensively used in many commercial recommender systems. Unfortunately, the computational complexity of these methods grows linearly with the number of customers that in typical commercial applications can grow to be several millions. To address these scalability concerns item-based recommendation techniques have been developed that analyze the user-item matrix to identify relations between the different items, and use these relations to compute the list of recommendations.In this paper we present one such class of item-based recommendation algorithms that first determine the similarities between the various items and then used them to identify the set of items to be recommended. The key steps in this class of algorithms are (i) the method used to compute the similarity between the items, and (ii) the method used to combine these similarities in order to compute the similarity between a basket of items and a candidate recommender item. Our experimental evaluation on five different datasets show that the proposed item-based algorithms are up to 28 times faster than the traditional user-neighborhood based recommender systems and provide recommendations whose quality is up to 27% better.}, acmid = {502627}, address = {New York, NY, USA}, author = {Karypis, George}, booktitle = {Proceedings of the Tenth International Conference on Information and Knowledge Management}, doi = {10.1145/502585.502627}, interhash = {ad804add9a1dec7cb4df3c98fac7dc13}, intrahash = {234c68832d68a4530e3ba8e2fb533043}, isbn = {1-58113-436-3}, location = {Atlanta, Georgia, USA}, numpages = {8}, pages = {247--254}, publisher = {ACM}, series = {CIKM '01}, title = {Evaluation of Item-Based Top-N Recommendation Algorithms}, url = {http://doi.acm.org/10.1145/502585.502627}, year = 2001 } @inproceedings{sarwar2001itembased, acmid = {372071}, address = {New York, NY, USA}, author = {Sarwar, Badrul and Karypis, George and Konstan, Joseph and Riedl, John}, booktitle = {Proceedings of the 10th international conference on World Wide Web}, doi = {10.1145/371920.372071}, interhash = {043d1aaba0f0b8c01d84edd517abedaf}, intrahash = {16f38785d7829500ed41c610a5eff9a2}, isbn = {1-58113-348-0}, location = {Hong Kong, Hong Kong}, numpages = {11}, pages = {285--295}, publisher = {ACM}, title = {Item-based collaborative filtering recommendation algorithms}, url = {http://doi.acm.org/10.1145/371920.372071}, year = 2001 } @article{zhang2010personalized, abstract = {Personalized recommender systems are confronting great challenges of accuracy, diversification and novelty, especially when the data set is sparse and lacks accessorial information, such as user profiles, item attributes and explicit ratings. Collaborative tags contain rich information about personalized preferences and item contents, and are therefore potential to help in providing better recommendations. In this article, we propose a recommendation algorithm based on an integrated diffusion on user–item–tag tripartite graphs. We use three benchmark data sets, Del.icio.us, MovieLens and BibSonomy, to evaluate our algorithm. Experimental results demonstrate that the usage of tag information can significantly improve accuracy, diversification and novelty of recommendations.}, author = {Zhang, Zi-Ke and Zhou, Tao and Zhang, Yi-Cheng}, doi = {10.1016/j.physa.2009.08.036}, interhash = {caa341f4d9ffb507dbf72f75a201dbd1}, intrahash = {8fc27ade71ea065b92874ba29fca711b}, issn = {0378-4371}, journal = {Physica A: Statistical Mechanics and its Applications}, number = 1, pages = {179 - 186}, title = {Personalized recommendation via integrated diffusion on user–item–tag tripartite graphs}, url = {http://www.sciencedirect.com/science/article/pii/S0378437109006839}, volume = 389, year = 2010 } @incollection{gemmell2010resource, abstract = {Collaborative tagging applications enable users to annotate online resources with user-generated keywords. The collection of these annotations and the way they connect users and resources produce a rich information space for users to explore. However the size, complexity and chaotic structure of these systems hamper users as they search for information. Recommenders can assist the user by suggesting resources, tags or even other users. Previous work has demonstrated that an integrative approach which exploits all three dimensions of the data (users, resources, tags) produce superior results in tag recommendation. We extend this integrative philosophy to resource recommendation. Specifically, we propose an approach for designing weighted linear hybrid resource recommenders. Through extensive experimentation on two large real world datasets, we show that the hybrid recommenders surpass the effectiveness of their constituent components while inheriting their simplicity, computational efficiency and explanatory capacity. We further introduce the notion of information channels which describe the interaction of the three dimensions. Information channels can be used to explain the effectiveness of individual recommenders or explain the relative contribution of components in the hybrid recommender.}, address = {Berlin/Heidelberg}, affiliation = {Center for Web Intelligence, School of Computing, DePaul University, Chicago, Illinois USA}, author = {Gemmell, Jonathan and Schimoler, Thomas and Mobasher, Bamshad and Burke, Robin}, booktitle = {E-Commerce and Web Technologies}, doi = {10.1007/978-3-642-15208-5_1}, editor = {Buccafurri, Francesco and Semeraro, Giovanni}, interhash = {357183305397b19624ec246b915df6ac}, intrahash = {684579385b3a4f90f5b41ce7c92ddb2a}, isbn = {978-3-642-15208-5}, keyword = {Computer Science}, pages = {1--12}, publisher = {Springer}, series = {Lecture Notes in Business Information Processing}, title = {Resource Recommendation in Collaborative Tagging Applications}, url = {http://dx.doi.org/10.1007/978-3-642-15208-5_1}, volume = 61, year = 2010 } @inproceedings{wang2010claper, abstract = {Classical papers are of great help for beginners to get familiar with a new research area. However, digging them out is a difficult problem. This paper proposes Claper, a novel academic recommendation system based on two proven principles: the Principle of Download Persistence and the Principle of Citation Approaching (we prove them based on real-world datasets). The principle of download persistence indicates that classical papers have few decreasing download frequencies since they were published. The principle of citation approaching indicates that a paper which cites a classical paper is likely to cite citations of that classical paper. Our experimental results based on large-scale real-world datasets illustrate Claper can effectively recommend classical papers of high quality to beginners and thus help them enter their research areas.}, author = {Wang, Yonggang and Zhai, Ennan and Hu, Jianbin and Chen, Zhong}, booktitle = {Proceedings of the seventh International Conference on Fuzzy Systems and Knowledge Discovery}, doi = {10.1109/FSKD.2010.5569227}, interhash = {7180ddaf1c1765a45fd244027bd0bf43}, intrahash = {7da72bf2f0538afad9377a0d50c263b4}, month = aug, pages = {2777--2781}, publisher = {IEEE}, title = {Claper: Recommend classical papers to beginners}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5569227}, volume = 6, year = 2010 } @inproceedings{he2011citation, abstract = {Automatic recommendation of citations for a manuscript is highly valuable for scholarly activities since it can substantially improve the efficiency and quality of literature search. The prior techniques placed a considerable burden on users, who were required to provide a representative bibliography or to mark passages where citations are needed. In this paper we present a system that considerably reduces this burden: a user simply inputs a query manuscript (without a bibliography) and our system automatically finds locations where citations are needed. We show that naïve approaches do not work well due to massive noise in the document corpus. We produce a successful approach by carefully examining the relevance between segments in a query manuscript and the representative segments extracted from a document corpus. An extensive empirical evaluation using the CiteSeerX data set shows that our approach is effective.}, acmid = {1935926}, address = {New York, NY, USA}, author = {He, Qi and Kifer, Daniel and Pei, Jian and Mitra, Prasenjit and Giles, C. Lee}, booktitle = {Proceedings of the fourth ACM international conference on Web search and data mining}, doi = {10.1145/1935826.1935926}, interhash = {7e98aaf26a7ed6cc624249a3ab570d7a}, intrahash = {bbd320f03d13c6cfff4b6f9e6b4630f7}, isbn = {978-1-4503-0493-1}, location = {Hong Kong, China}, numpages = {10}, pages = {755--764}, publisher = {ACM}, title = {Citation recommendation without author supervision}, url = {http://doi.acm.org/10.1145/1935826.1935926}, year = 2011 } @inproceedings{bethard2010should, abstract = {Scientists depend on literature search to find prior work that is relevant to their research ideas. We introduce a retrieval model for literature search that incorporates a wide variety of factors important to researchers, and learns the weights of each of these factors by observing citation patterns. We introduce features like topical similarity and author behavioral patterns, and combine these with features from related work like citation count and recency of publication. We present an iterative process for learning weights for these features that alternates between retrieving articles with the current retrieval model, and updating model weights by training a supervised classifier on these articles. We propose a new task for evaluating the resulting retrieval models, where the retrieval system takes only an abstract as its input and must produce as output the list of references at the end of the abstract's article. We evaluate our model on a collection of journal, conference and workshop articles from the ACL Anthology Reference Corpus. Our model achieves a mean average precision of 28.7, a 12.8 point improvement over a term similarity baseline, and a significant improvement both over models using only features from related work and over models without our iterative learning.}, acmid = {1871517}, address = {New York, NY, USA}, author = {Bethard, Steven and Jurafsky, Dan}, booktitle = {Proceedings of the 19th ACM international conference on Information and knowledge management}, doi = {10.1145/1871437.1871517}, interhash = {1cdf6c7da38af251279e9fb915266af2}, intrahash = {369206c7472baeaa5ecefef586e16c6a}, isbn = {978-1-4503-0099-5}, location = {Toronto, ON, Canada}, numpages = {10}, pages = {609--618}, publisher = {ACM}, title = {Who should I cite: learning literature search models from citation behavior}, url = {http://doi.acm.org/10.1145/1871437.1871517}, year = 2010 } @incollection{springerlink:10.1007/978-3-642-01307-2_55, address = {Berlin/Heidelberg}, affiliation = {Department of Computer Science and Technology, Tsinghua University, Beijing, 100084 China}, author = {Tang, Jie and Zhang, Jing}, booktitle = {Advances in Knowledge Discovery and Data Mining}, doi = {10.1007/978-3-642-01307-2_55}, editor = {Theeramunkong, Thanaruk and Kijsirikul, Boonserm and Cercone, Nick and Ho, Tu-Bao}, interhash = {c429474403bcd28561f8ab4fa436d036}, intrahash = {983b4eaae55e0d5e5c628a13bf58324c}, isbn = {978-3-642-01306-5}, keyword = {Computer Science}, pages = {572--579}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {A Discriminative Approach to Topic-Based Citation Recommendation}, url = {http://dx.doi.org/10.1007/978-3-642-01307-2_55}, volume = 5476, year = 2009 } @inproceedings{he2010contextaware, abstract = {When you write papers, how many times do you want to make some citations at a place but you are not sure which papers to cite? Do you wish to have a recommendation system which can recommend a small number of good candidates for every place that you want to make some citations? In this paper, we present our initiative of building a context-aware citation recommendation system. High quality citation recommendation is challenging: not only should the citations recommended be relevant to the paper under composition, but also should match the local contexts of the places citations are made. Moreover, it is far from trivial to model how the topic of the whole paper and the contexts of the citation places should affect the selection and ranking of citations. To tackle the problem, we develop a context-aware approach. The core idea is to design a novel non-parametric probabilistic model which can measure the context-based relevance between a citation context and a document. Our approach can recommend citations for a context effectively. Moreover, it can recommend a set of citations for a paper with high quality. We implement a prototype system in CiteSeerX. An extensive empirical evaluation in the CiteSeerX digital library against many baselines demonstrates the effectiveness and the scalability of our approach.}, acmid = {1772734}, address = {New York, NY, USA}, author = {He, Qi and Pei, Jian and Kifer, Daniel and Mitra, Prasenjit and Giles, Lee}, booktitle = {Proceedings of the 19th international conference on World wide web}, doi = {10.1145/1772690.1772734}, interhash = {d48586d4ee897859c5d797e671f3e384}, intrahash = {17f7aa5c8bf1d9055fd83688f46fde65}, isbn = {978-1-60558-799-8}, location = {Raleigh, North Carolina, USA}, numpages = {10}, pages = {421--430}, publisher = {ACM}, title = {Context-aware citation recommendation}, url = {http://doi.acm.org/10.1145/1772690.1772734}, year = 2010 } @inproceedings{Strohman:2007:RCA:1277741.1277868, abstract = {We approach the problem of academic literature search by considering an unpublished manuscript as a query to a search system. We use the text of previous literature as well as the citation graph that connects it to find relevant related material. We evaluate our technique with manual and automatic evaluation methods, and find an order of magnitude improvement in mean average precision as compared to a text similarity baseline.}, acmid = {1277868}, address = {New York, NY, USA}, author = {Strohman, Trevor and Croft, W. Bruce and Jensen, David}, booktitle = {Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval}, doi = {10.1145/1277741.1277868}, interhash = {a34279add7d7a9f3c564735b7b8dcd44}, intrahash = {7a0b1ff2a40b3989ef8d83daabd91159}, isbn = {978-1-59593-597-7}, location = {Amsterdam, The Netherlands}, numpages = {2}, pages = {705--706}, publisher = {ACM}, title = {Recommending citations for academic papers}, url = {http://doi.acm.org/10.1145/1277741.1277868}, year = 2007 } @electronic{priem2010scientometrics, abstract = {The growing flood of scholarly literature is exposing the weaknesses of current, citation-based methods of evaluating and filtering articles. A novel and promising approach is to examine the use and citation of articles in a new forum: Web 2.0 services like social bookmarking and microblogging. Metrics based on this data could build a “Scientometics 2.0,” supporting richer and more timely pictures of articles' impact. This paper develops the most comprehensive list of these services to date, assessing the potential value and availability of data from each. We also suggest the next steps toward building and validating metrics drawn from the social Web.}, author = {Priem, Jason and Hemminger, Bradely H.}, interhash = {d38dfec4da93265575aff99a811839d9}, intrahash = {b95d32eed9419fefc007245914faad98}, journal = {First Monday; Volume 15, Number 7 - 5 July 2010}, title = {Scientometrics 2.0: New metrics of scholarly impact on the social Web}, url = {http://www.uic.edu/htbin/cgiwrap/bin/ojs/index.php/fm/article/view/2874/2570}, year = 2010 } @inproceedings{mcnee2002recommending, abstract = {Collaborative filtering has proven to be valuable for recommending items in many different domains. In this paper, we explore the use of collaborative filtering to recommend research papers, using the citation web between papers to create the ratings matrix. Specifically, we tested the ability of collaborative filtering to recommend citations that would be suitable additional references for a target research paper. We investigated six algorithms for selecting citations, evaluating them through offline experiments against a database of over 186,000 research papers contained in ResearchIndex. We also performed an online experiment with over 120 users to gauge user opinion of the effectiveness of the algorithms and of the utility of such recommendations for common research tasks. We found large differences in the accuracy of the algorithms in the offline experiment, especially when balanced for coverage. In the online experiment, users felt they received quality recommendations, and were enthusiastic about the idea of receiving recommendations in this domain.}, acmid = {587096}, address = {New York, NY, USA}, author = {McNee, Sean M. and Albert, Istvan and Cosley, Dan and Gopalkrishnan, Prateep and Lam, Shyong K. and Rashid, Al Mamunur and Konstan, Joseph A. and Riedl, John}, booktitle = {Proceedings of the 2002 ACM conference on Computer supported cooperative work}, doi = {10.1145/587078.587096}, interhash = {7178849aab57a025dff76e177d64be9b}, intrahash = {50f94e753fad76222bd33cbe591f9360}, isbn = {1-58113-560-2}, location = {New Orleans, Louisiana, USA}, numpages = {10}, pages = {116--125}, publisher = {ACM}, series = {CSCW '02}, title = {On the recommending of citations for research papers}, url = {http://doi.acm.org/10.1145/587078.587096}, year = 2002 } @incollection{liang2011finding, abstract = {With the tremendous amount of research publications, recommending relevant papers to researchers to fulfill their information need becomes a significant problem. The major challenge to be tackled by our work is that given a target paper, how to effectively recommend a set of relevant papers from an existing citation network. In this paper, we propose a novel method to address the problem by incorporating various citation relations for a proper set of papers, which are more relevant but with a very limited size. The proposed method has two unique properties. Firstly, a metric called Local Relation Strength is defined to measure the dependency between cited and citing papers. Secondly, a model called Global Relation Strength is proposed to capture the relevance between two papers in the whole citation graph. We evaluate our proposed model on a real-world publication dataset and conduct an extensive comparison with the state-of-the-art baseline methods. The experimental results demonstrate that our method can have a promising improvement over the state-of-the-art techniques.}, address = {Berlin/Heidelberg}, affiliation = {Department of Computer Science, City University of Hong Kong, Hong Kong, China}, author = {Liang, Yicong and Li, Qing and Qian, Tieyun}, booktitle = {Web-Age Information Management}, doi = {10.1007/978-3-642-23535-1_35}, editor = {Wang, Haixun and Li, Shijun and Oyama, Satoshi and Hu, Xiaohua and Qian, Tieyun}, interhash = {73c03c97c82d13d66f791001dd65688d}, intrahash = {3c1d75d4210de5cc1f5325598847c046}, isbn = {978-3-642-23534-4}, keyword = {Computer Science}, pages = {403--414}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Finding Relevant Papers Based on Citation Relations}, url = {http://dx.doi.org/10.1007/978-3-642-23535-1_35}, volume = 6897, year = 2011 } @inproceedings{McNee:2006:AEA:1125451.1125659, abstract = {Recommender systems have shown great potential to help users find interesting and relevant items from within a large information space. Most research up to this point has focused on improving the accuracy of recommender systems. We believe that not only has this narrow focus been misguided, but has even been detrimental to the field. The recommendations that are most accurate according to the standard metrics are sometimes not the recommendations that are most useful to users. In this paper, we propose informal arguments that the recommender community should move beyond the conventional accuracy metrics and their associated experimental methodologies. We propose new user-centric directions for evaluating recommender systems.}, acmid = {1125659}, address = {New York, NY, USA}, author = {McNee, Sean M. and Riedl, John and Konstan, Joseph A.}, booktitle = {CHI '06 extended abstracts on Human factors in computing systems}, doi = {10.1145/1125451.1125659}, interhash = {fe396fbce5daacd374196ad688e3f149}, intrahash = {4b9fddbd766a9247856641989a778b23}, isbn = {1-59593-298-4}, location = {Montr\&\#233;al, Qu\&\#233;bec, Canada}, numpages = {5}, pages = {1097--1101}, publisher = {ACM}, series = {CHI EA '06}, title = {Being accurate is not enough: how accuracy metrics have hurt recommender systems}, url = {http://doi.acm.org/10.1145/1125451.1125659}, year = 2006 } @inproceedings{puertamelguizo2008personalized, abstract = {Writing is a complex task and several computer systems have been developed in order to support writing. Most of these systems, however, are mainly designed with the purpose of supporting the processes of planning, organizing and connecting ideas. In general, these systems help writers to formulate external visual representations of their ideas and connections of the main topics that should be addressed in the paper, sequence of the sections, etc. With the advent of the world wide web, writing and finding information for the written text has become increasingly intertwined. Consequently, it is necessary to develop systems able to support the task of finding relevant information during writing, without interfering with the writing process proper. In this paper we present the Proactive Recommender System: A propos. This system is being developed in order to support writers in the difficult task of finding appropriate relevant information during writing. We raise the question whether the tendency to interleave (re)search and writing implies a need for developing more comprehensive models of the cognitive processes involved in writing scientific and policy papers. }, author = {Puerta Melguizo, Mari Carmen and Muñoz Ramos, Olga and Boves, Lou and Bogers, Toine and van den Bosch, Antal}, booktitle = {Proceedings of the Workshop on Natural Language Processing resources, algorithms and tools for authoring aids}, editor = {and}, interhash = {264e2eeb8c9417f8dc974d22e5502ae9}, intrahash = {5a29342d397e1c4e7f783029fc134620}, pages = {21--26}, title = {A Personalized Recommender System for Writing in the Internet Age }, url = {http://repository.dlsi.ua.es/251/1/workshops/W23_Proceedings.pdf#page=27}, year = 2008 } @article{gedikli2010rating, author = {Gedikli, Fatih and Jannach, Dietmar}, interhash = {7a4e1b28558c54b576678146c5a614fe}, intrahash = {e7380137d10bd6a765897ea54bd05a31}, journal = {Systems and the Social Web at ACM }, title = {Rating items by rating tags}, year = 2010 } @inproceedings{heck2011testing, author = {Heck, Tamara and Peters, Isabella and Stock, Wolfgang G.}, booktitle = {Workshop on Recommender Systems and the Social Web (ACM RecSys'11)}, interhash = {d250a0eb45ca7c198d9cdb238802fd74}, intrahash = {8b68db4ae61ec5c97010fbec2ddaa6c6}, title = {Testing collaborative filtering against co-citation analysis and bibliographic coupling for academic author recommendation}, year = 2011 } @presentation{noauthororeditor, author = {leaong, Sheryl}, interhash = {94d316680af6c91206302e964f2d7918}, intrahash = {03ec5a6b30883646ee0c489630656b04}, title = {A survey of recommender systems for scientific papers}, year = 2012 } @inproceedings{parra2009evaluation, abstract = {Motivated by the potential use of collaborative tagging systems to develop new recommender systems, we have implemented and compared three variants of user-based collaborative filtering algorithms to provide recommendations of articles on CiteULike. On our first approach, Classic Collaborative filtering (CCF), we use Pearson correlation to calculate similarity between users and a classic adjusted ratings formula to rank the recommendations. Our second approach, Neighbor-weighted Collaborative Filtering (NwCF), incorporates the amount of raters in the ranking formula of the recommendations. A modified version of the Okapi BM25 IR model over users ’ tags is implemented on our third approach to form the user neighborhood. Our results suggest that incorporating the number of raters into the algorithms leads to an improvement of precision, and they also support that tags can be considered as an alternative to Pearson correlation to calculate the similarity between users and their neighbors in a collaborative tagging system. }, author = {Parra, Denis and Brusilovsky, Peter}, booktitle = {Proceedings of the Workshop on Web 3.0: Merging Semantic Web and Social Web}, interhash = {03a51e24ecab3ad66fcc381980144fea}, intrahash = {42773258c36ccf2f59749991518d1784}, issn = {1613-0073}, location = {Torino, Italy}, month = jun, series = {CEUR Workshop Proceedings}, title = {Evaluation of Collaborative Filtering Algorithms for Recommending Articles on CiteULike}, url = {http://ceur-ws.org/Vol-467/paper5.pdf}, volume = 467, year = 2009 } @inproceedings{lee2010using, abstract = {This paper aims to combine information about users' self-defined social connections with traditional collaborative filtering (CF) to improve recommendation quality. Specifically, in the following, the users' social connections in consideration were groups. Unlike other studies which utilized groups inferred by data mining technologies, we used the information about the groups in which each user explicitly participated. The group activities are centered on common interests. People join a group to share and acquire information about a topic as a form of community of interest or practice. The information of this group activity may be a good source of information for the members. We tested whether adding the information from the users' own groups or group members to the traditional CF-based recommendations can improve the recommendation quality or not. The information about groups was combined with CF using a mixed hybridization strategy. We evaluated our approach in two ways, using the Citeulike data set and a real user study.}, acmid = {1864752}, address = {New York, NY, USA}, author = {Lee, Danielle H. and Brusilovsky, Peter}, booktitle = {Proceedings of the fourth ACM conference on Recommender systems}, doi = {10.1145/1864708.1864752}, interhash = {6fd1cbcfd94da174c910d9144467372a}, intrahash = {ec592568ca4a9f6b2ebaf41816af1ebc}, isbn = {978-1-60558-906-0}, location = {Barcelona, Spain}, numpages = {4}, pages = {221--224}, publisher = {ACM}, title = {Using self-defined group activities for improving recommendations in collaborative tagging systems}, url = {http://doi.acm.org/10.1145/1864708.1864752}, year = 2010 }