P Bedi, R Sharma/ Expert Systems with Applications 39(2012)1183-1190 Collaborative Filtering based recommender system. Also, compar- Goldberg, K, Roeder, T- Gupta, D& Perkins, C(2001).Eigentaste: A constant time ing the performance of TARS on both the datasets taking different collaborative filtering algorithm. Information Retrieval Jourmal. 4(2). 133-151 sparseness levels into account, precision using jester dataset is in- Herlocker, ). L, Konstan, J. A, Terveen, L G, Reidl, ].(2004). Evaluating ased approximately by 5.8% at time t=O and by 3.6% at time t>0 as compared to MovieLens dataset. Hill, w,Stead, L Rosenstein, M.& Furnas, G (1995). Recommending and evaluatin 5 Conclusions Addison-wesley p crisping systems. Denver Colorado, United States, ACM Press/ The success of Collaborative Filtering technology depends on Konstan, J.A., Miller, B N, Maltz, D, Herlocker, J. L Gordon, LR,& Riedl,]. (1997). r ne f a peer neighborhood containing similar users is a vital function Lorenzi. F. Santos. DSdo azzan, ALC(2005). Case-based recommender for generating valuable recommendations. In the sparse data envi- Congresso da Sociedade Braseilera de Computacao, Sao Leopolda, pp. 752-76 ronment, the predicted recommendations often depend on a small Massa, P& Avesani, P(2004). Trust-aware collaborative filtering for recommender portion of the selected neighborhood. In our proposed system TARS, sparseness in user similarity due to data sparsity of input Massa). P. Avesani. P: (2007), Prust-aware recommender systems Dynamic trust pheromone updation for each user in the directed esra sys s bhattacharjee B, (2004) Using trust in recommender systers: a- gement. Oxford, England, pp. 221-235. his recommendation partner. It indicates that trustw iness of a Massa, P. Avesani, P( 2009) Trust metrics in recommender systems. computing partner is the function of the time and inter-operation between the ith Social Trust. London: Springer, pp. 259-285, doi: 10. 1007/ 978-1-84800- 56-9 graph, the optimal trust path is searched effectively resulting in the 10th International Conference on Intelligent User Interfaces(IUr05), San Diego, for recommendation by providing addition information along with Resnick, P, Lakoya pp 167-12k ak, M, Bergstrom, P& Riedl, J. (1994). GroupLens: An open architecture for collaborative filtering of Netnews, in Proceedings of the the predicted rating regarding the level of connectedness in trust cooperative work, Chapel Hil, North graph from where recommendations are generated, items and number of neighbors involved in predicting rating. This not only es user satisfaction, but also helps users make better deci- Rich, E(1979). User modeling via stereotypes. Cognitive Science Journal. Elsevier. ions as it acts as an indication of confidence of the predicted rat ng. Also, new users highly benefit from pheromone updating J,& MuhIhauser, M.(2006). A Classification of trust systems. 06. Berlin: Springer, pp S strategy known from ant algorithms. The Many are smarter than Sarwar, B M, Karypis, G, Konstan, J. A& Reidl, J.(2000a). Analysis of the Few and users benefit from this wisdom of crowds as positive feedback in the form of aggregated dynamic trust pheromone de- tion generation application which has input in the form of r-item rating matrix. The performance of TARS is evaluated Sarw度MKm0mm账mr毁 nstan,.A& Riedl, ]. (2001) Item-based collaborative using Jester dataset and MovieLens dataset available online and compared with traditional Collaborative Filtering based approach Schafer. J. B, Konstan, J.A,& Reidl, J(1999) Recommender systems in E- for generating recommendations. It is found that our approach generates better results as compared to traditional CF based Schafer, J.B. Frankowski locker, -& Sen, S (2007) Collaborative filtering Springer,pp.291-324SBN:9783-540-72078-2 on Human Factors in Computing Systems, Denver, Colorado, United Basu, C, Hirsh, H,& Cohen social and content-based information in recommendation, in Proceedings of the Sharma, R, Singh, M, Makkar, R, Kaur, H, Bedi, P (2007). Ant Recommender: Artificial Intelligence (AAAl-98) Madison, ecommender system inspired by ant colony, in Proceedings of international nference on Advances in Computer Vision and Information Technology(ACVI- R, Kaur, H(2009). Recommender System based on collaborativ n using ant 998) Learning collaborative information filters, in Proceedings of the Fifteenth International Conference on Machine Learning, Terveer en L. Hill. w. Amento. B D. er,J (1997). PHOAKS: A system sharingrecommendationsCommunicationsoftheAcm,40(3),59-62.http:// Blum, C(2005) Ant Colony Optimization: Introduction and recent trends. Physics Bonjplrev. 2005 10.00, Journal, Elsevier, 2(4). pp. 353-373. doi: 10.1016/ Terveen, L,& Hill, W(2001). Human-Computer collaboration in recommender puter 487-509) neraulaz, rom natural mplexity ew York). ISBN: 0-19-51315s Burke, R(2002). Hybrid rec 31.doi:10.1109/s1s2003.1202257 ng and User-Adapted Interaction Journal 12(4). L ge. D Procedintley P3.(2003). Particle Swarm Optimization recommender system. or E-Co A:1008286413827 Dorigo, M, Maniezzo, v,& Colorni, A (1996) Ant System: Optimization by a colony hengdu,pp.14,lSBN:1-4244-0885-7,doi:10.1109 ICSSSM20074280307 nsactions on Systems, Man, and Cybernetics-PartB, Yuan, w Guan, D, Lee, Y. K Lee, S,& Hur, SI(2010). Improved trust-aware oldness of trust networks. Knowledge- Dorigo, M, Stutzle, T (2004). Ant Colony Optimization. Cambridge, MA: MIT Press. BN0-262-04219 Ziegler, C N.& Nicolas, G..(2007). Investigating correlations of trust and interest Goldberg, D, Nicholas, D, Oki, B. M,& Terry, D.(1992). Using collaborative similarity- Do birds of a feather really flock together? Decision Support Systems, fltering to weave an informatio try. Co cations of the ACM, 35(12) 43(2).460-475 61-70Collaborative Filtering based recommender system. Also, compar￾ing the performance of TARS on both the datasets taking different sparseness levels into account, precision using Jester dataset is in￾creased approximately by 5.8% at time t = 0 and by 3.6% at time t > 0 as compared to MovieLens dataset. 5. Conclusions The success of Collaborative Filtering technology depends on the process of locating people with similar neighbors. The selection of a peer neighborhood containing similar users is a vital function for generating valuable recommendations. In the sparse data envi￾ronment, the predicted recommendations often depend on a small portion of the selected neighborhood. In our proposed system TARS, sparseness in user similarity due to data sparsity of input matrix is reduced while creating directed trust graph for each user. Dynamic trust pheromone updation for each user in the directed trust graph reflects the degree to which an active user might trust his recommendation partner. It indicates that trustworthiness of a partner is the function of the time and inter-operation between the two partners. By applying ant colony algorithm on directed trust graph, the optimal trust path is searched effectively resulting in best neighborhood. Further our approach is used as an explanation for recommendation by providing addition information along with the predicted rating regarding the level of connectedness in trust graph from where recommendations are generated, items and number of neighbors involved in predicting rating. This not only improves user satisfaction, but also helps users make better deci￾sions as it acts as an indication of confidence of the predicted rat￾ing. Also, new users highly benefit from pheromone updating strategy known from ant algorithms. The Many are smarter than the Few and users benefit from this wisdom of crowds as positive feedback in the form of aggregated dynamic trust pheromone de- fines ‘‘popularity’’ of a user as recommender over a period of time. Our proposed approach can be implemented for any recommenda￾tion generation application which has input in the form of user–item rating matrix. The performance of TARS is evaluated using Jester dataset and MovieLens dataset available online and compared with traditional Collaborative Filtering based approach for generating recommendations. It is found that our approach generates better results as compared to traditional CF based approach. References Basu, C., Hirsh, H., & Cohen, W.W. (1998). Recommendation as classification: using social and content-based information in recommendation, in Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98). Madison, Wisconsin, AAAI Press, pp. 714–720. Bedi, P., Sharma, R., & Kaur, H. (2009). Recommender System based on collaborative behavior of ants, Journal of Artificial Intelligence 2009, Asian Network for Scientific Information, ISSN 1994–5450, pp. 40–55. Billsus, D. &. Pazzani, M. J. (1998). Learning collaborative information filters, in Proceedings of the Fifteenth International Conference on Machine Learning, Madison, Morgan Kaufman San Francisco, CA, pp. 46–54. Blum, C. (2005). Ant Colony Optimization: Introduction and recent trends. Physics of Life Reviews Journal, Elsevier, 2(4), pp. 353–373. doi:10.1016/ j.plrev.2005.10.001. Bonabeau, E., Dorigo, M. & Theraulaz, G. (1999). Swarm Intelligence: From natural to artificial systems. Santa Fe Institute Studies in the Sciences of Complexity, Oxford University Press (New York). ISBN: 0-19-513158-4, Kindle Edition. Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction Journal, 12(4), 331–370. doi:10.1023/ A:1008286413827. Dorigo, M., Maniezzo, V., & Colorni, A. (1996). Ant System: Optimization by a colony of cooperating agents. IEEE Transactions on Systems, Man, and Cybernetics-Part B, 26(1), 29–41. Dorigo, M., & Stutzle, T. (2004). Ant Colony Optimization. Cambridge, MA: MIT Press. ISBN 0-262-04219-3. Goldberg, D., Nicholas, D., Oki, B. M., & Terry, D. (1992). Using collaborative filtering to weave an information tapestry. Communications of the ACM, 35(12), 61–70. Goldberg, K., Roeder, T., Gupta, D., & Perkins, C. (2001). Eigentaste: A constant time collaborative filtering algorithm. Information Retrieval Journal, 4(2), 133–151. doi:10.1.1.37.8212. Herlocker, J. L., Konstan, J. A., Terveen, L. G., & Reidl, J. (2004). Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems, 22(1), 5–53. doi:10.1145/963770.963772. Hill, W., Stead, L., Rosenstein, M. & Furnas, G. (1995). Recommending and evaluating choices in a virtual community of use, in Proceedings of the SIGCHI conference on Human factors in computing systems, Denver, Colorado, United States, ACM Press/ Addison-Wesley Publishing Co., pp. 194–201. Konstan, J. A., Miller, B. N., Maltz, D., Herlocker, J. L., Gordon, L. R., & Riedl, J. (1997). GroupLens: Applying collaborative filtering to UseNet news. Communications of the ACM, 40(3), 77–87. http://doi.acm.org/10.1145/245108.245126. Lorenzi, F., Santos, D.S.dos & Bazzan, A.L.C. (2005). Case-based recommender systems inspired by social insects, in Proceedings of XXV Congresso da Sociedate Braseilera de Computacao, Sao Leopolda, pp. 752–760. Massa, P., & Avesani, P. (2004). Trust-aware collaborative filtering for recommender systems, in Proceedings of International Conference on Cooperative Information Systems, Agia Napa, Cyprus, pp. 492–508. Massa, P., & Avesani, P. (2007). Trust-aware recommender systems, Proceedings of RecSys, ACM, New York, NY, USA, pp. 17–24. Massa, P. & Bhattacharjee, B. (2004). Using trust in recommender systems: an experimental analysis. in Proceedings of 2nd International Conference on trust management, Oxford, England, pp. 221–235. Massa, P., & Avesani, P. (2009). Trust metrics in recommender systems. Computing with Social Trust. London: Springer, pp. 259–285, doi:10.1007/978-1-84800- 356-9. O’Donovan, J., & Smith, B. (2005). Trust in recommender systems, in Proceedings of the 10th International Conference on Intelligent User Interfaces (IUI’05), San Diego, California, USA, pp. 167–174. Resnick, P., Lakovou, N., Sushak, M., Bergstrom, P. & Riedl, J. (1994). GroupLens: An open architecture for collaborative filtering of Netnews, in Proceedings of the 1994 ACM conference on Computer supported cooperative work, Chapel Hill, North Carolina, United States, ACM Press, pp. 175–186. Resnick, P., & Varian, H. R. (1997). Recommender systems. Communications of the ACM, 40(3), 56–58. doi:10.1145/245108.245121. Rich, E. (1979). User modeling via stereotypes. Cognitive Science Journal, Elsevier, 3(4), 329–354. doi:10.1207/s15516709cog0304_3. Ries, S., Kangasharju, J., & Muhlhauser, M. (2006). A Classification of trust systems, LNCS 4277/2006. Berlin: Springer, pp. 894–903. Sarwar, B. M., Karypis, G., Konstan, J. A. & Reidl, J. (2000a). Analysis of recommendation algorithms for E-Commerce. in Proceedings of the 2nd ACM conference on electronic commerce (EC’00), Minneapolis, Minnesota, United States, pp. 158–167. doi:10.1145/352871.352887. Sarwar, B. M., Karypis, G., Konstan, J. A. & Reidl, J. (2000b). Application of dimensionality reduction in recommender system – A case study. ACM WebKDD 2000 Web mining for E-commerce workshop. Sarwar, B. M., Karypis, G., Konstan, J. A. & Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms, in Proceedings of the 10th international conference on World Wide Web, Hong Kong, ACM Press, pp. 285–295. Schafer, J. B., Konstan, J. A., & Reidl, J. (1999). Recommender systems in E￾Commerce, in Proceedings of the first ACM conference on electronic commerce 99, Denver, United States, ACM Press, pp.158–166. Schafer, J. B., Frankowski, D., Herlocker, J., & Sen, S. (2007). Collaborative filtering recommender systems. The Adaptive Web LNCS 4321/2007. Berlin/Heidelberg: Springer, pp. 291-324ISBN: 978-3-540-72078-2. Shardanand, U., & Maes, P. (1995). Social information filtering: Algorithms for automating ‘Word of Mouth’, in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Denver, Colorado, United States, pp. 210–217. Sharma, R., Singh, M., Makkar, R., Kaur, H., & Bedi, P. (2007). Ant Recommender: Recommender system inspired by ant colony, in Proceedings of International Conference on Advances in Computer Vision and Information Technology (ACVIT- 07), pp. 361–369. Sobecki, J. (2007). Web-based system user interface hybrid recommendation using ant colony metaphor. LNCS 4694/2008. Berlin/Heidelberg: Springer, pp.1033–1040, ISBN: 978-3-540-74828-1. Terveen, L., Hill, W., Amento, B., McDonald, D., & Creter, J. (1997). PHOAKS: A system for sharing recommendations. Communications of the ACM, 40(3), 59–62. http:// doi.acm.org/10.1145/245108.245122. Terveen, L., & Hill, W. (2001). Human–Computer collaboration in recommender systems. In Human computer interaction in the new millenium (pp. 487–509). New York: Addision-Wesley. Ujjin, S., & Bentley, P.J. (2003). Particle Swarm Optimization recommender system, in Proceedings of the 2003 IEEE Swarm Intelligence Symposium-SIS‘03, pp. 124– 131. doi:10.1109/SIS.2003.1202257. Wei, Z. (2007). A novel trust model based on recommendation for E-Commerce, in International Conference on Service Systems and Service Management 2007, Chengdu, pp. 1-4, ISBN: 1-4244-0885-7, doi:10.1109/ICSSSM.2007.4280307. Yuan, W., Guan, D., Lee, Y. K., Lee, S., & Hur, S. J. (2010). Improved trust-aware recommender system using small-worldness of trust networks. Knowledge￾Based Systems, 23(3), 232–238. doi:10.1016/j.knosys.2009.12.004. Ziegler, C. N., & Nilcolas, G. J. (2007). Investigating correlations of trust and interest similarity- Do birds of a feather really flock together? Decision Support Systems, 43(2), 460–475. 1190 P. Bedi, R. Sharma / Expert Systems with Applications 39 (2012) 1183–1190