Abstract

Context-aware recommender systems incorporate contextual information when generating item recommendations. Previous studies indicate that collaborative filtering (CF) is a simple, intuitive, and widely used technique for this purpose. However, in context-aware CF, user preferences are often filtered based on the exact matching of all contextual features, which leads to data sparsity. Moreover, traditional similarity measures used in CF generally do not account for contextual information when computing similarities. In this paper, a framework was proposed to address these limitations by generating recommendations through a CF approach enhanced with context relaxation, context similarity, and context weighting. These mechanisms help alleviate the issue of data sparsity. Furthermore, novel similarity measures were introduced in the framework to incorporate not only contextual information but also the global and local rating behaviors of users. An empirical evaluation using two context-aware datasets revealed the effectiveness of the proposed technique compared to existing methods. The framework is applicable across multiple domains regardless of the contextual dimensions involved, making it a practical solution for real-world recommendation problems.

Keywords

Context-aware recommender systems, Collaborative filtering, Context relaxation, Similarity measures, Data sparsity, User rating behavior.

References

[1] Li Y, Liu K, Satapathy R, Wang S, Cambria E. Recent developments in recommender systems: a survey. IEEE Computational Intelligence Magazine. 2024; 19(2):78-95.

[2] Wang L, Joty S, Gao W, Zeng X, Wong KF. Improving conversational recommender system via contextual and time-aware modeling with less domain-specific knowledge. IEEE Transactions on Knowledge and Data Engineering. 2024; 36(11):6447-61.

[3] Adomavicius G, Tuzhilin A. Context-aware recommender systems. In recommender systems handbook 2010 (pp. 217-53). Boston, MA: Springer US.

[4] Champiri ZD, Shahamiri SR, Salim SS. A systematic review of scholar context-aware recommender systems. Expert Systems with Applications. 2015; 42(3):1743-58.

[5] Liu Q, Chen N, Sakai T, Wu XM. Once: boosting content-based recommendation with both open-and closed-source large language models. In proceedings of the 17th ACM international conference on web search and data mining 2024 (pp. 452-61). ACM.

[6] Deldjoo Y, Schedl M, Knees P. Content-driven music recommendation: evolution, state of the art, and challenges. Computer Science Review. 2024; 51:100618.

[7] TR M, Vinoth KV, Lim SJ. UsCoTc: improved collaborative filtering (CFL) recommendation methodology using user confidence, time context with impact factors for performance enhancement. PLoS One. 2023; 18(3):1-22.

[8] Pardo E, Valdiviezo-diaz P, Barba-guaman L, Chicaiza J. Collaborative filtering recommendation systems based on deep learning: an experimental study. In world conference on information systems and technologies 2024 (pp. 54-63). Cham: Springer Nature Switzerland.

[9] Hasan MR, Ferdous J. Dominance of AI and machine learning techniques in hybrid movie recommendation system applying text-to-number conversion and cosine similarity approaches. Journal of Computer Science and Technology Studies. 2024; 6(1):94-102.

[10] Keikhosrokiani P, Fye GM. A hybrid recommender system for health supplement e-commerce based on customer data implicit ratings. Multimedia Tools and Applications. 2024; 83(15):45315-44.

[11] Alfarhood S, Alfarhood M. CAML: a context-aware metric learning approach for improved recommender systems. Alexandria Engineering Journal. 2024; 100:53-60.

[12] Abinaya S, Ramya R. Enhancement in context-aware recommender systems–a systematic review. In second international conference on emerging trends in information technology and engineering (ICETITE) 2024 (pp. 1-13). IEEE.

[13] Mao C, Wu Z, Liu Y, Shi Z. Matrix factorization recommendation algorithm based on attention interaction. Symmetry. 2024; 16(3):1-20.

[14] Darmawan FA, Baizal ZK. An approach to a group movie recommender system using matrix factorization-based collaborative filtering. Jurnal Infotel. 2024; 16(2):243-54.

[15] Behera G, Nain N. Collaborative filtering with temporal features for movie recommendation system. Procedia Computer Science. 2023; 218:1366-73.

[16] Sánchez-moreno D, López BVF, Muñoz VMD, Sánchez LÁL, Moreno-garcía MN. Social network community detection to deal with gray-sheep and cold-start problems in music recommender systems. Information. 2024; 15(3):1-17.

[17] Zheng Y. Non-dominated differential context modeling for context-aware recommendations. Applied Intelligence. 2022; 52(9):10008-21.

[18] Patra BK, Launonen R, Ollikainen V, Nandi S. A new similarity measure using Bhattacharyya coefficient for collaborative filtering in sparse data. Knowledge-Based Systems. 2015; 82:163-77.

[19] Košir A, Odić A, Kunaver M, Tkalčič M, Tasič JF. Database for contextual personalization= podatkovna baza za kontekstualno personalizacijo. Elektrotehniski Vestnik. 2011; 78(5):270-4.

[20] Baltrunas L, Kaminskas M, Ludwig B, Moling O, Ricci F, Aydin A, et al. Incarmusic: context-aware music recommendations in a car. In international conference on electronic commerce and web technologies 2011 (pp. 89-100). Berlin, Heidelberg: Springer Berlin Heidelberg.

[21] Shafiee S. Unveiling the latest trends and advancements in machine learning algorithms for recommender systems: a literature review. Procedia CIRP. 2024; 121:115-20.

[22] Huynh HX, Phan NQ, Pham NM, Pham VH, Son LH, Abdel-basset M, et al. Context-similarity collaborative filtering recommendation. IEEE Access. 2020; 8:33342-51.

[23] Dixit VS, Jain P. Weighted percentile-based context-aware recommender system. In applications of artificial intelligence techniques in engineering: SIGMA 2018 (pp. 377-88). Singapore: Springer Singapore.

[24] Dixit VS, Jain P, Gupta S. Proposed RCFS-cars framework with noise detection and correction. Applied Artificial Intelligence. 2019; 33(4):361-77.

[25] Iftikhar A, Ghazanfar MA, Ayub M, Alahmari SA, Qazi N, Wall J. A reinforcement learning recommender system using bi-clustering and Markov decision process. Expert Systems with Applications. 2024; 237:1-18.

[26] Wang J, Gao S, Tang Z, Tan D, Cao B, Fan J. A context-aware recommendation system for improving manufacturing process modeling. Journal of Intelligent Manufacturing. 2023; 34(3):1347-68.

[27] Ji Y, Jiang Z, Li X, Huang Y, Wang F. A multitask context-aware approach for design lesson-learned knowledge recommendation in collaborative product design. Journal of Intelligent Manufacturing. 2023; 34(4):1615-37.

[28] Mu Y, Wu Y. Multimodal movie recommendation system using deep learning. Mathematics. 2023; 11(4):1-12.

[29] Ibrahim M, Bajwa IS, Sarwar N, Hajjej F, Sakr HA. An intelligent hybrid neural collaborative filtering approach for true recommendations. IEEE Access. 2023; 11:64831-49.

[30] Widayanti R, Chakim MH, Lukita C, Rahardja U, Lutfiani N. Improving recommender systems using hybrid techniques of collaborative filtering and content-based filtering. Journal of Applied Data Sciences. 2023; 4(3):289-302.

[31] Anter A, Moawad IF, Mosaad SM. Enhancing E-learning materials recommendations with contextual awareness and collaborative filtering. In 6th international conference on computing and informatics (ICCI) 2024 (pp. 452-8). IEEE.

[32] Liu X, Wu L. FAGRec: alleviating data sparsity in POI recommendations via the feature-aware graph learning. Electronic Research Archive. 2024; 32(4):2728−44.

[33] Liu H, Hu Z, Mian A, Tian H, Zhu X. A new user similarity model to improve the accuracy of collaborative filtering. Knowledge-Based Systems. 2014; 56:156-66.

[34] Chaparala P, Muppa LD, Shaik A. Empirical investigation on similarity measures used in recommendation systems. In 15th international conference on computing communication and networking technologies (ICCCNT) 2024 (pp. 1-7). IEEE.

[35] Dixit VS, Jain P. Proposed similarity measure using Bhattacharyya coefficient for context aware recommender system. Journal of Intelligent & Fuzzy Systems. 2019; 36(4):3105-17.

[36] Anwar K, Zafar A, Iqbal A. An efficient approach for improving the predictive accuracy of multi-criteria recommender system. International Journal of Information Technology. 2024; 16(2):809-16.

[37] Reddy DK, Nayak J, Behera HS, Shanmuganathan V, Viriyasitavat W, Dhiman G. A systematic literature review on swarm intelligence based intrusion detection system: past, present and future. Archives of Computational Methods in Engineering. 2024; 31(5):2717.

[38] Bratton D, Kennedy J. Defining a standard for particle swarm optimization. In swarm intelligence symposium 2007 (pp. 120-7). IEEE.

[39] Zheng Y. A revisit to the identification of contexts in recommender systems. In companion proceedings of the 20th international conference on intelligent user interfaces 2015 (pp. 133-6). ACM.

[40] Odić A, Tkalčič M, Tasič J, Košir A. Relevant context in a movie recommender system: users’ opinion vs. statistical detection. In context-aware recommender systems: proceedings of the 4th workshop on context-aware recommender systems in conjunction with the 6th ACM conference on recommender systems (RecSys 2012) 2012 (pp.1-5). ACM.

[41] Zheng Y, Burke R, Mobasher B. Recommendation with differential context weighting. In international conference on user modeling, adaptation, and personalization 2013 (pp. 152-64). Berlin, Heidelberg: Springer Berlin Heidelberg.

[42] Ujjin S, Bentley PJ. Particle swarm optimization recommender system. In proceedings of the IEEE swarm intelligence symposium. 2003 (pp. 124-31). IEEE.

[43] Kuo RJ, Li SS. Applying particle swarm optimization algorithm-based collaborative filtering recommender system considering rating and review. Applied Soft Computing. 2023; 135:110038.

[44] Ferdousi ZV, Colazzo D, Negre E. Correlation-based pre-filtering for context-aware recommendation. In international conference on pervasive computing and communications workshops (PerCom Workshops) 2018 (pp. 89-94). IEEE.

Cite this article