تولید توضیح شخصی سازی شده برای سیستم پیشنهاددهنده لیست توئیتر مبتنی بر شباهت معنایی هشتگ ها
محورهای موضوعی : فناوری اطلاعات و دانشحوا علیزاده نوقابی 1 , بهشید بهکمال 2 * , صالحه ناصری 3 , محسن کاهانی 4
1 - گروه مهندسی کامپیوتر، دانشگاه فردوسی مشهد
2 - عضو هیات علمی
3 - گروه مهندسی کامپیوتر، دانشگاه فردوسی مشهد
4 - استاد
کلید واژه: سیستم های پیشنهاددهنده توضیح پذیر, توضیح شخصی سازی شده, لیست توئیتر, شباهت معنایی هشتگ ها,
چکیده مقاله :
امروزه سیستم‌های پشنهاددهنده ی لیست های توئیتر با بکارگیری اطلاعات مختلف کاربران و لیستها و همچنین اعمال الگوریتمهای پیچیده، توانسته اند به دقت بالایی در پیش بینی برسند و پیشنهادهای مرتبط با هر کاربر را تولید کنند، اما قابلیت توضیح پذیری در این سیستم ها به عنوان یک چالش مطرح می باشد. توضیح مناسب به همراه یک لیست پیشنهادشده علاوه بر افزایش اعتماد و رضایت کاربران، می تواند به آنها در تصمیم‌گیری آگاهانه کمک نماید. از این رو در این مقاله، یک مدل تولید توضیح ارائه میشود که به ایجاد خودکار یک توصیف برای لیست پیشنهادشده بصورت شخصی سازی شده برای کاربر مدنظر می پردازد. بطور دقیقتر، این مدل با انتخاب هشتگهای پرتکرار از محتوای لیست که ارتباط معنایی با تاریخچه فعالیت های قبلی کاربر دارد، سعی میکند موضوع لیست را به گونهای قابل درک و شخصی سازی شده در قالب یک توضیح همراه با لیست پیشنهادشده نمایش دهد. پس از جمع آوری یک مجموعه داده واقعی از شبکه توئیتر، با انجام آزمایش‌ها نشان داده شد که مدل پیشنهادی قادر به تولید توضیح برای درصد بالایی از پیشنهادهای ایجادشده براساس یک مدل پیشنهاددهنده پایه میب اشد.
Twitter List recommender systems have achieved high prediction accuracy by leveraging diverse user and List information alongside complex algorithms. However, explainability remains a significant challenge in these systems. Providing meaningful explanations along with a set of recommendations can enhance user trust and satisfaction, assisting them in informed decision-making. In this paper, we present a model for the automated generation of personalized descriptions as explanations for recommended Twitter Lists. Specifically, our model selects frequently used hashtags from the content of the recommended List, establishing semantic relationships with the user's activity history. The aim is to present the List's subject in an understandable and personalized manner through a generated description. Through experiments conducted on a real Twitter dataset, our proposed model demonstrates its capability to generate explanations for a high percentage of the recommendations provided by a recommendation model.
[1] S. de la Rouviere and K. Ehlers, “Lists as coping strategy for information overload on Twitter,” presented at the Proceedings of the 22nd International Conference on World Wide Web, 2013, pp. 199–200.
[2] V. Rakesh, D. Singh, B. Vinzamuri, and C. K. Reddy, “Personalized recommendation of twitter lists using content and network information,” presented at the Proceedings of the International AAAI Conference on Web and Social Media, 2014, pp. 416–425.
[3] L. Chen, Y. Zhao, S. Chen, H. Fang, C. Li, and M. Wang, “iplug: Personalized list recommendation in twitter,” presented at the Web Information Systems Engineering–WISE 2013: 14th International Conference, Nanjing, China, October 13-15, 2013, Proceedings, Part II 14, Springer, 2013, pp. 88–103.
[4] C.-H. Tsai and P. Brusilovsky, “The effects of controllability and explainability in a social recommender system,” User Modeling and User-Adapted Interaction, vol. 31, pp. 591–627, 2021.
[5] D. Shmaryahu, G. Shani, and B. Shapira, “Post-hoc Explanations for Complex Model Recommendations using Simple Methods.,” presented at the IntRS@ RecSys, 2020, pp. 26–36.
[6] Y. Zhang and X. Chen, “Explainable recommendation: A survey and new perspectives,” Foundations and Trends® in Information Retrieval, vol. 14, no. 1, pp. 1–101, 2020.
[7] I. Nunes and D. Jannach, “A systematic review and taxonomy of explanations in decision support and recommender systems,” User Modeling and User-Adapted Interaction, vol. 27, pp. 393–444, 2017.
[8] K. Balog and F. Radlinski, “Measuring recommendation explanation quality: The conflicting goals of explanations,” presented at the Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval, 2020, pp. 329–338.
[9] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
[10] M. Caro-Martínez, G. Jiménez-Díaz, and J. A. Recio-García, “Conceptual modeling of explainable recommender systems: an ontological formalization to guide their design and development,” Journal of Artificial Intelligence Research, vol. 71, pp. 557–589, 2021.
[11] C. Nóbrega and L. Marinho, “Towards explaining recommendations through local surrogate models,” presented at the Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, 2019, pp. 1671–1678.
[12] G. Peake and J. Wang, “Explanation mining: Post hoc interpretability of latent factor models for recommendation systems,” presented at the Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, pp. 2060–2069.
[13] C. Lonjarret, C. Robardet, M. Plantevit, R. Auburtin, and M. Atzmueller, “Why should i trust this item? explaining the recommendations of any model,” presented at the 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA), IEEE, 2020, pp. 526–535.
[14] Y. Zhang, G. Lai, M. Zhang, Y. Zhang, Y. Liu, and S. Ma, “Explicit factor models for explainable recommendation based on phrase-level sentiment analysis,” presented at the Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, 2014, pp. 83–92.
[15] N. Wang, H. Wang, Y. Jia, and Y. Yin, “Explainable recommendation via multi-task learning in opinionated text data,” presented at the The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018, pp. 165–174.
[16] H. Wang et al., “Ripplenet: Propagating user preferences on the knowledge graph for recommender systems,” presented at the Proceedings of the 27th ACM international conference on information and knowledge management, 2018, pp. 417–426.
[17] Q. Ai, V. Azizi, X. Chen, and Y. Zhang, “Learning heterogeneous knowledge base embeddings for explainable recommendation,” Algorithms, vol. 11, no. 9, p. 137, 2018.
[18] Y. Xian, Z. Fu, S. Muthukrishnan, G. De Melo, and Y. Zhang, “Reinforcement knowledge graph reasoning for explainable recommendation,” presented at the Proceedings of the 42nd international ACM SIGIR conference on research and development in information retrieval, 2019, pp. 285–294.
[19] F. Fusco, M. Vlachos, V. Vasileiadis, K. Wardatzky, and J. Schneider, “RecoNet: An Interpretable Neural Architecture for Recommender Systems.,” presented at the IJCAI, 2019, pp. 2343–2349.
[20] Y. Lu, R. Dong, and B. Smyth, “Why I like it: multi-task learning for recommendation and explanation,” presented at the Proceedings of the 12th ACM Conference on Recommender Systems, 2018, pp. 4–12.
[21] Z. Chen et al., “Co-attentive multi-task learning for explainable recommendation.,” presented at the IJCAI, 2019, pp. 2137–2143.
[22] X. Wang, X. He, F. Feng, L. Nie, and T.-S. Chua, “Tem: Tree-enhanced embedding model for explainable recommendation,” presented at the Proceedings of the 2018 world wide web conference, 2018, pp. 1543–1552.
[23] W. Ma et al., “Jointly learning explainable rules for recommendation with knowledge graph,” presented at the The world wide web conference, 2019, pp. 1210–1221.
[24] W. Sherchan, S. Nepal, and C. Paris, “A survey of trust in social networks,” ACM Computing Surveys (CSUR), vol. 45, no. 4, pp. 1–33, 2013.
[25] B. Wang, M. Ester, J. Bu, and D. Cai, “Who also likes it? generating the most persuasive social explanations in recommender systems,” presented at the Proceedings of the AAAI Conference on Artificial Intelligence, 2014.
[26] C. Shi, Z. Zhang, P. Luo, P. S. Yu, Y. Yue, and B. Wu, “Semantic path based personalized recommendation on weighted heterogeneous information networks,” presented at the Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, 2015, pp. 453–462.
[27] Y. Zhang, X. Xu, H. Zhou, and Y. Zhang, “Distilling structured knowledge into embeddings for explainable and accurate recommendation,” presented at the Proceedings of the 13th international conference on web search and data mining, 2020, pp. 735–743.
[28] J. Zheng, Z. Qin, S. Wang, and D. Li, “Attention-based explainable friend link prediction with heterogeneous context information,” Information Sciences, vol. 597, pp. 211–229, 2022.
[29] Z. Ren, S. Liang, P. Li, S. Wang, and M. de Rijke, “Social collaborative viewpoint regression with explainable recommendations,” presented at the Proceedings of the tenth ACM international conference on web search and data mining, 2017, pp. 485–494.
[30] Y. Wu and M. Ester, “Flame: A probabilistic model combining aspect based opinion mining and collaborative filtering,” presented at the Proceedings of the eighth ACM international conference on web search and data mining, 2015, pp. 199–208.
[31] Y. Zhang, “Incorporating phrase-level sentiment analysis on textual reviews for personalized recommendation,” presented at the Proceedings of the eighth ACM international conference on web search and data mining, 2015, pp. 435–440.
[32] D. Kim, Y. Jo, I.-C. Moon, and A. Oh, “Analysis of twitter lists as a potential source for discovering latent characteristics of users,” presented at the ACM CHI workshop on microblogging, Citeseer, 2010.
[33] C. Lu, W. Lam, and Y. Zhang, “Twitter user modeling and tweets recommendation based on wikipedia concept graph,” presented at the Workshops at the Twenty-Sixth AAAI conference on artificial intelligence, 2012.
[34] R. Egger and J. Yu, “A topic modeling comparison between lda, nmf, top2vec, and bertopic to demystify twitter posts,” Frontiers in sociology, vol. 7, p. 886498, 2022.
[35] M. Grootendorst, “BERTopic: Neural topic modeling with a class-based TF-IDF procedure,” arXiv preprint arXiv:2203.05794, 2022.