پیش بینی پیوند مبتنی بر اعتماد با استفاده از مدل محاسبات فازی در شبکه های اجتماعی علامت دار
محورهای موضوعی : هوش مصنوعی و رباتیکفاطمه حسین خانی 1 , علی هارون آبادی 2 , سعید ستایشی 3
1 - گروه مهندسی کامپیوتر، دانشکده فنی و مهندسی، واحد تهران مرکز، دانشگاه آزاد اسلامی، تهران، ایران
2 - استادیار، گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، واحد تهران مرکزی، دانشگاه آزاد اسلامی، تهران، ایران
3 - دانشگاه صنعتی امیر کبیر
کلید واژه: پیش بینی پیوند, شبکه های اجتماعی علامت دار, اعتماد, عدم اعتماد, محاسبات فازی ,
چکیده مقاله :
پیش بینی پیوند امری ضروری برای بررسی پیوند بین گره ها در شبکه های اجتماعی است. گسترش و مدل سازی شبکه های اجتماعی منجر به پیدایش شبکه های اجتماعی به صورت علامت دار، جهت دار و وزنی می شود. روابط کاربران در شبکه های اجتماعی علامت دار جنبه های ذهنی و نامتقارن وابسته به این حوزه را تعریف می کنند، لذا هر دو اصطلاح اعتماد و عدم اعتماد چالش برانگیز هستند. برای حل مسئله پراکندگی در شبکه ها و غلبه بر ابهام در روابط، یک روش اعتماد-عدم اعتماد مبتنی بر محاسبات فازی برای محاسبه قدرت پیوندها پیشنهاد می شود. هدف روش پیشنهادی پیش بینی پیوند برای حل مسئله پراکندگی در شبکه های اجتماعی علامت دار با ترکیب ویژگی های توصیف کاربران در شبکه های اجتماعی است که با تاثیر مستقیم گره های برتر و تاثیر غیرمستقیم گره های معمولی بر پیشبینی رتبهبندی ها ارزیابی می شود. اعتماد با یک سیستم فازی ممدانی مبتنی بر ویژگی های انعکاس شباهت فازی، اعتماد کلی و عدم اعتماد کلی تعیین می شود. ارزیابی روش پیشنهادی با معیار دقت بر روی مجموعه داده های شبکه های اجتماعی Epinions وSlashdot انجام شد. دقت روش پیشنهادی در مجموعه داده هایEpinions و Slashdotبه ترتیب برابر 0.991 و 0.998 می باشد. نتایج به دست آمده نشان می دهد روش پیشنهادی نسبت به مشکل پراکندگی داده ها در شبکه های اجتماعی علامت دار قوی عمل می-کند و این اثربخشی مدل پیشنهادی را بیان می نماید.
Link prediction is an important to check link between nodes in social networks. The modeling of social networks leads to emergence of signed, directed and weighted social networks. The relationships of users in social networks are characterized by subjective, asymmetric and ambiguous aspects related to this domain, then both terms of trust and distrust are challenging. To solve the problem of sparsity in networks and overcome ambiguity in relationships, a trust-distrust method based on fuzzy computational is proposed to calculate strength of links. The purpose of proposed link prediction is to solve problem of sparsity in signed social networks by combining descriptive features of users with the direct influence of top nodes and the indirect influence of common nodes on rating prediction. Trust is determined by a Mamdani fuzzy system based on mirroring of similarity fuzzy features, overall trust and overall distrust. The evaluation of the proposed method was done with the accuracy measure on datasets of Epinions and Slashdot. The accuracy of proposed method in Epinions and Slashdot datasets is 0.991 and 0.998, respectively. The obtained results show that proposed method works well for problem of data sparsity in signed social networks and show the effectiveness of proposed model.
[1] X.Li, H.Fang, and J.Zhang, “FILE: A novel framework for predicting social status in signed networks”, Thirty-Second AAAI Conference on Artificial Intelligence, AAAI18 - Artificial Intelligence and the Web, Vol.32, No.1, 2018, PP.330–337.
[2] K.Akilal, M.Omar, and H.Slimani, “Characterizing and using gullibility, competence, and reciprocity in a very fast and robust trust and distrust inference algorithm for weighted signed social networks”, Knowledge-Based Systems, Vol.192, 2020, PP.1-11.
[3] H.Shirgahi, M.Mohsenzadeh, and H.H.S.Javadi, “A new method of trust mirroring estimation based on social networks parameters by fuzzy system”, International Journal Machine Learning & Cybernetics, Springer. Vol.9, 2018, PP.1153–1168.
[4] V.Kant, and KK.Bharadwaj, Fuzzy computational models of trust and distrust for enhanced recommendations, International Journal of Intelligent Systems, Vol.28, 2013, PP.332–365.
[5] N.Girdhar, S.Minz, and K.K.Bharadwaj, “Link prediction in signed social networks based on fuzzy computational model of trust and distrust”, Soft Computing, Vol.23, 2019, PP.12123–12138.
[6] Z.Duan, W.Xu, Y.Chen, and L.Ding, “ETBRec: a novel recommendation algorithm combining the double influence of trust relationship and expert users”, Applied Intelligence, Vol.52, 2022, PP.282–294.
[7] N.D.Nur, A.H.Sitil, S.Muntadher, S.Firdaus, and N.Anuar, “Applications of link prediction in social networks: A review”, Journal of Network and Computer Appllicatins, Vol.166, 2020, PP.1-31.
[8] X.Zhu, and Y.Ma, “Sign Prediction on Social Networks Based Nodal Features”, Journal of Complexity, Vol.2020, 2020, PP.1-11.
[9] R.E.Veras De Sena Rosa, F.A.S.Guimarães, R.d.S.Mendonça and V.F.d.Lucena, “Improving Prediction Accuracy in Neighborhood-Based Collaborative Filtering by Using Local Similarity”, IEEE Access, Vol.8, 2020, PP.142795-142809.
[10] H.Ghorbanzadeh, A.Sheikhahmadi, M.Jalili, and S.Sulaimany, “A Hybrid Method of Link Prediction in Directed Graphs”, Expert Systems with Applications, Vol.165, 2020, PP.1-13.
[11] D.Wang, Da-wei, Y.Yih and M.Ventresca, “Improving neighbor-based collaborative filtering by using a hybrid similarity measurement”, Expert Systems with Applications, Vol.160, 2020, PP.1-23.
[12] X.Wang, Y.Chai, H.Li, and D.Wu, “Link prediction in heterogeneous information networks: An improved deep graph convolution approach”, Decision Support Systems, Vol.141, 2021, PP.113448-113460.
[13] H.Tahmasbi, M.Jalali, and H.Shakeri, “TSCMF: Temporal and social collective matrix factorization model for recommender systems”, Journal of Intelligence Information Systems, Vol.56, 2021, PP.169–187.
[14] C.He, H.Liu, Y.Tang, S.Liu, X.Fei, Q.Cheng, and H.Li, “Similarity preserving overlapping community detection in signed networks”, Future Generation Computer Systems, Vol.116, 2021, PP.275-290.
[15] R.I.Yaghi, H.Faris, I.Aljarah, A.M.Al-Zoubi, A.A.Heidari, and S.Mirjalili, “Link Prediction Using Evolutionary Neural Network Models”, Evolutionary Machine Learning Techniques, Vol.32, 2020, PP.85-112.
[16] R.E.Tillman, P.Vamsi, Ch.Jiahao, R.Prashant and M.Veloso, “Heuristics for Link Prediction in Multiplex Networks”, In Proceedings of ECAI'2020, 24th European Conference on Artificial Intelligence, Vol.325, 2020, PP.1938-1945.
[17] F.Guo, W.Zhou, Z.Wang, Ch.Ju, Sh.Ji, Q.Lu, "A link prediction method based on topological nearest-neighbors similarity in directed networks", Journal of Computational Science, Vol.69, 2023, PP.102002-102016.
[18] H.Liu, Z.Zhenzhen, B.Fan, H.Zeng, Y.Zhang, and G.Jiang, “PrGCN: Probability prediction with graph convolutional network for person re-identification”, Neurocomputing, Vol.423, 2021, PP.57-70.
[19] X.Hu, X.Xiong, Y.Wu, M.Shi, P.Wei, and Ch.Ma, "A Hybrid Clustered SFLA-PSO algorithm for optimizing the timely and real-time rumor refutations in Online Social Networks", Expert Systems with Applications, Vol.212, 2023, PP.118638-118670.
[20] Y.Xu, Z.Feng, X.Zhou, M.Xing, H.Wu, X.Xue, Sh.Chen, Ch.Wang and L.Qi, "Attention-based neural networks for trust evaluation in online social networks", Information Sciences, Vol.630, 2023, PP.507-522.
[21] M.Nooraei.Abadeh, M.Mirzaie, “A differential machine learning approach for trust prediction in signed social networks”, Supercomput, Vol.79, 2023, PP.9443–9466.
[22] T.Zhang, W.Li, L.Wang, and J.Yang, “Social recommendation algorithm based on stochastic gradient matrix decomposition in social network”, Journal of Ambient Intelligence and Humanized Computing. Vol.11, 2020, PP.601-608.
[23] P.Srilatha, R.Manjula, and C.P.Kumar, “Link Prediction on Social Attribute Network Using Lévy Flight Firefly Optimization”, Advances in Artificial Intelligence and Data Engineering, Vol.1133, 2021, PP.1299-1309.
[24] E.Nasiri, K.Berahmand, and Y.Li, “Robust graph regularization nonnegative matrix factorization for link prediction in attributed networks”, Multimedia Tools and Applications, Vol.82, 2023, PP.3745–3768.
[25] S.Ghasemi, and A.Zarei., “Improving link prediction in social networks using local and global features: a clustering-based approach, Progress in Artificial”, Intelligence, Vol.11, 2022, PP.79–92.
[26] Suryakant, and T.Mahara, A New Similarity Measure Based on Mean Measure of Divergence for Collaborative Filtering in Sparse Environment, Procedia Computer Science, Vol.89, 2016, PP.450–456.
[27] https://snap.stanford.edu/data/soc-Epinions1. html,Last Visited (01, October. 2022).
[28] http://snap.stanford.edu/data/soc-Slashdot0902.html, Last Visited (01, October.2022).
[29] J.Golbeck, “Combining provenance with trust in social networks for semantic content filtering”, International Provenance and Annotation Workshop, Vol.4145, 2006, PP.101–108.