Good Times Bad Times: A Study on Recency Effects in Collaborative Filtering for Social Tagging
作者： Santiago Larrain , Christoph Trattner , Denis Parra , Eduardo Graells-Garrido , Kjetil Nørvåg
关键词: Recommender system 、 Function (engineering) 、 MovieLens 、 Similarity (psychology) 、 Context (language use) 、 Computer science 、 Information retrieval 、 Data mining 、 Stability (learning theory) 、 Temporal information 、 Collaborative filtering
摘要: In this paper, we present work-in-progress of a recently started project that aims at studying the effect time in recommender systems context social tagging. Despite existence previous work area, no research has yet made an extensive evaluation and comparison time-aware recommendation methods. With motivation, paper presents results study where focused on understanding (i) "when" to use temporal information into traditional collaborative filtering (CF) algorithms, (ii) "how" weight similarity between users items by exploring different time-decay functions. As our conducted over five tagging (Delicious, BibSonomy, CiteULike, MovieLens, Last.fm) suggest, step (when) which is incorporated CF algorithm substantial accuracy, type function (how) plays role accuracy coverage mostly under pre-filtering user-based CF, while item-based shows stronger stability experimental conditions.
acm.org
christophtrattner.info
elsevier.com
puc.cl
uc.cl 
researchgate.net 参考文章(19)
Dominik Kowald, Christoph Trattner, Emanuel Lacic, Paul Christian Seitlinger, Denis Parra, Recommending Items in Social Tagging Systems Using Tag and Time Information HT (Doctoral Consortium / Late-breaking Results / Workshops). pp. 4- 9 ,(2014)
Dengneng Wu, Zhenming Yuan, Kai Yu, Hong Pan, Temporal Social Tagging Based Collaborative Filtering Recommender for Digital Library international conference on asian digital libraries. pp. 199- 208 ,(2012) , 10.1007/978-3-642-34752-8_26
Robert Jäschke, Leandro Marinho, Andreas Hotho, Lars Schmidt-Thieme, Gerd Stumme, None, Tag Recommendations in Folksonomies european conference on principles of data mining and knowledge discovery. pp. 506- 514 ,(2007) , 10.1007/978-3-540-74976-9_52
Zhenming Yuan, Tianhao Yu, Jia Zhang, A social tagging based collaborative filtering recommendation algorithm for digital library international conference on asian digital libraries. pp. 192- 201 ,(2011) , 10.1007/978-3-642-24826-9_25
Dominik Kowald, Paul Seitlinger, Christoph Trattner, Tobias Ley, Long time no see: the probability of reusing tags as a function of frequency and recency the web conference. pp. 463- 468 ,(2014) , 10.1145/2567948.2576934
T LEE, Y PARK, Y PARK, A time-based approach to effective recommender systems using implicit feedback Expert Systems With Applications. ,vol. 34, pp. 3055- 3062 ,(2008) , 10.1016/J.ESWA.2007.06.031
Dan Li, Peng Cao, Yucui Guo, Min Lei, Time Weight Update Model Based on the Memory Principle in Collaborative Filtering Journal of Computers. ,vol. 8, pp. 2763- 2767 ,(2013) , 10.4304/JCP.8.11.2763-2767
Jonathan L. Herlocker, Joseph A. Konstan, Loren G. Terveen, John T. Riedl, Evaluating collaborative filtering recommender systems ACM Transactions on Information Systems. ,vol. 22, pp. 5- 53 ,(2004) , 10.1145/963770.963772
Dominik Kowald, Emanuel Lacic, Christoph Trattner, TagRec: towards a standardized tag recommender benchmarking framework acm conference on hypertext. pp. 305- 307 ,(2014) , 10.1145/2631775.2631781
Cheng-Lung Huang, Po-Han Yeh, Cheng-Wei Lin, Den-Cing Wu, Utilizing user tag-based interests in recommender systems for social resource sharing websites Knowledge Based Systems. ,vol. 56, pp. 86- 96 ,(2014) , 10.1016/J.KNOSYS.2013.11.001