Multimedia Tools and Applications

, Volume 78, Issue 3, pp 2667–2687 | Cite as

Improving music recommendation by incorporating social influence

  • Jinpeng ChenEmail author
  • Pinguang Ying
  • Ming Zou


In the past decades, a large number of music pieces are uploaded to the Internet every day through social networks, such as, Spotify and YouTube, that concentrates on music and videos. We have been witnessing an ever-increasing amount of music data. At the same time, with the huge amount of online music data, users are facing an everyday struggle to obtain their interested music pieces. To solve this problem, music search and recommendation systems are helpful for users to find their favorite content from a huge repository of music. However, social influence, which contains rich information about similar interests between users and users’ frequent correlation actions, has been largely ignored in previous music recommender systems. In this work, we explore the effects of social influence on developing effective music recommender systems and focus on the problem of social influence aware music recommendation, which aims at recommending a list of music tracks for a target user. To exploit social influence in social influence aware music recommendation, we first construct a heterogeneous social network, propose a novel meta path-based similarity measure called WPC, and denote the framework of similarity measure in this network. As a step further, we use the topological potential approach to mine social influence in heterogeneous networks. Finally, in order to improve music recommendation by incorporating social influence, we present a factor graphic model based on social influence. Our experimental results on one real world dataset verify that our proposed approach outperforms current state-of-the-art music recommendation methods substantially.


Music recommendation Topological potential Social influence Meta-Path 



This work is supported by the National Natural Science Foundation of China under Grant No.61702043, and the Fundamental Research Funds for the Central Universities under Grant No. 500417062.


  1. 1.
    Aizenberg N, Koren Y, Somekh O (2012) Build your own music recommender by modeling internet radio streams[C]. International Conference on World Wide Web. ACM, pp 1–10Google Scholar
  2. 2.
    Althoff T, Jindal P, Leskovec J (2017) Online actions with offline impact: How online social networks influence online and offline user behavior[C]. Proceedings of the Tenth ACM International Conference on Web Search and Data Mining. ACM, pp 537–546Google Scholar
  3. 3.
    Ben-Elazar S, Lavee G, Koenigstein N et al (2017) Groove radio: A bayesian hierarchical model for personalized playlist Generation[C]. Tenth ACM international conference on web search and data mining. ACM, pp 445–453Google Scholar
  4. 4.
    Bilanakos C, Sotiropoulos DN, Georgoula I et al (2015) Optimal influence strategies in social Networks[J]. Soc Sci Electron Publ 49(4):1–45Google Scholar
  5. 5.
    Chang H-Y, Huang S-C, Wu J-H (2017) A personalized music recommendation system based on electroencephalography feedback. Multimed Tools Appl 76.19:19523–19542CrossRefGoogle Scholar
  6. 6.
    Cheng Z, Shen J, Mei T (2014) Just-for-me: an adaptive personalization system for location-aware social music recommendation. SIGIR, pp 1267–1268Google Scholar
  7. 7.
    Cheng Z, Shen J (2016) On effective location-aware music recommendation[J]. Acm Trans Inf Syst 34(2):1–32MathSciNetCrossRefGoogle Scholar
  8. 8.
    Cheng Z, Shen J, Hoi SCH (2016) On effective personalized music retrieval by exploring online user Behaviors[C]. International ACM SIGIR conference on research and development in information retrieval. ACM, pp 125–134Google Scholar
  9. 9.
    Cheng Z, Shen J, Nie L, Chua T-S, Kankanhalli M (2017) Exploring User-Specific Information in Music Retrieval. In proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, pp 655–664Google Scholar
  10. 10.
    Cheng Z, Shen J, L Zhu et al (2017) Exploiting music play sequence for music recommendation[c] twenty-sixth international joint conference on artificial intelligence, pp 3654–3660Google Scholar
  11. 11.
    Craw S, Horsburgh B, Massie S (2015) Music recommenders: user evaluation without real users?[C] International Conference on Artificial Intelligence. AAAI Press, pp 1749–1755Google Scholar
  12. 12.
    Deng Z, Sang J, Xu C (2013) Personalized video recommendation based on cross-platform user modeling. ICME, pp 1–6Google Scholar
  13. 13.
    Dieleman S, Schrauwen B (2013) Deep content-based music recommendation[C]. International Conference on Neural Information Processing Systems. curran Associates Inc., pp 2643–2651Google Scholar
  14. 14.
    Ferwerda B, Schedl M (2014) Enhancing music recommender systems with personality information and emotional states: A proposal. In: Proceedings of UMAPGoogle Scholar
  15. 15.
    Fujino H, Hasida K, Matsubara Y (2017) Music exploration by impression based Interaction[C] ACM workshop on exploratory search and interactive data analytics. ACM, pp 55–58Google Scholar
  16. 16.
    Gillhofer M, Jogging SM (2015) Iron Maiden While Debussy for Dinner?[M] MultiMedia Modeling. Springer International Publishing, BerlinGoogle Scholar
  17. 17.
    Guo C, Liu X (2015) Automatic feature generation on heterogeneous graph for music recommendation[C] international ACM SIGIR conference on research and development in information retrieval. ACM, pp 807–810Google Scholar
  18. 18.
    Hariri N, Mobasher B, Burke R (2012) Context-aware music recommendation based on latenttopic sequential patterns[C]. ACM Conference on Recommender Systems. ACM, pp 131–138Google Scholar
  19. 19.
    Hung H-J, Shuai H-H, Yang D-N, Huang L-H, Lee WC, Pei J, Chen M-S (2016) When social influence meets item inference. In: Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining. ACM, pp 915–924Google Scholar
  20. 20.
    Ivanov S, Theocharidis K, Terrovitis M et al (2017) Content recommendation for viral social Influence[C]. International ACM SIGIR conference on research and development in information retrieval. ACM, pp 565–574Google Scholar
  21. 21.
    Jannach D, Lerche L, Kamehkhosh I (2015) Beyond “hitting the hits”: generating coherent music playlist continuations with the right tracks[c], pp 187–194Google Scholar
  22. 22.
    Kaminskas M, Ricci F, Schedl M (2013) Location-aware music recommendation using auto-tagging and hybrid matching[C]. ACM Conference on Recommender Systems. ACM, pp 17–24Google Scholar
  23. 23.
    Knees P, Schedl M (2013) A survey of music similarity and recommendation from music context data[J]. Acm Trans Multimed Comput Commun Appl 10(1):1–21CrossRefGoogle Scholar
  24. 24.
    Lichtenwalter R, Lussier JT, Chawla NV (2010) New perspectives and methods in link prediction. In: Kdd’10, pp 243–252Google Scholar
  25. 25.
    Lu L et al (2012) Learning influence from heterogeneous social networks. Data mining and knowledge discovery 25.3, pp 511–544Google Scholar
  26. 26.
    Lu Y, Qiao Z, Zhang P et al (2017) Ranking-Based music recommendation in online music Radios[C]. IEEE international conference on data science in cyberspace. IEEE, pp 614–619Google Scholar
  27. 27.
    Moshfeghi Y, Piwowarski B, Jose JM (2011) Handling data sparsity in collaborative filtering using emotion and semantic based features[C]. International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, pp 625–634Google Scholar
  28. 28.
    Onori M, Micarelli A, Sansonetti G (2016) A comparative analysis of Personality-Based music recommender systems. In: Empire@ RecSys, pp 55–59Google Scholar
  29. 29.
    Pálovics R, Benczúr A A, Kocsis L et al (2014) Exploiting temporal influence in online recommendation. Proceedings of the 8th ACM Conference on Recommender systems. ACM, pp 273–280Google Scholar
  30. 30.
    Qi Q, Chen Z, Liu J et al Using inferred tag ratings to improve user-based collaborative filtering. ACM Symposium on Applied Computing. ACM, 2012:2008–2013Google Scholar
  31. 31.
    Sang J, Mei T, Xu C (2015) Activity sensor: Check-in usage mining for local recommendation[m]. ACM TIST 6(3):41:1–41:24Google Scholar
  32. 32.
    Schedl M, Vall A, Farrahi K (2014) User geospatial context for music recommendation in microblogs[C]. International ACM SIGIR Conference on Research andamp; Development in Information Retrieval. ACM, pp 987–990Google Scholar
  33. 33.
    Schedl M, Hauger D (2015) Tailoring music recommendations to users by considering diversity, mainstreaminess, and Novelty[C]. International ACM SIGIR conference on research and development in information retrieval. ACM, pp 947–950Google Scholar
  34. 34.
    Schedl M, Hauger D, Farrahi K et al (2015) On the influence of user characteristics on music recommendation Algorithms[C]. European conference on ir research, ECIR 2015, proceedings, pp 339–345Google Scholar
  35. 35.
    Seo YD, Kim YG, Lee E et al (2017) Personalized recommender system based on friendship strength in social network services[J]. Expert Syst Appl 69:135–148CrossRefGoogle Scholar
  36. 36.
    Su JH, Chang WY, Tseng VS (2017) Effective social content-based collaborative filtering for music recommendation[J]. Intell Data Anal 21:S195–S216CrossRefGoogle Scholar
  37. 37.
    Sun J, Tang J (2011) A survey of models and algorithms for social influence Analysis[M]. Social network data analytics. Springer, USGoogle Scholar
  38. 38.
    Tang W, Zhuang H, Tang J (2011) Learning to infer social ties in large networks[c]. Joint european conference on machine learning and knowledge discovery in databases. Springer, BerlinGoogle Scholar
  39. 39.
    Ugander J, Backstrom L, Marlow C et al (2012) Structural diversity in social contagion[J]. Proc Natl Acad Sci US Amer 109(16):5962CrossRefGoogle Scholar
  40. 40.
    Wang X, Wang Y (2014) Improving Content-based and Hybrid Music Recommendation using Deep Learning[C]. ACM International Conference on Multimedia. ACM, pp 627–636Google Scholar
  41. 41.
    Wang D, Liu S, Liu S et al (2016) Improving music recommendation using distributed Representation[C]. International conference companion on world wide web. international world wide web conferences steering committee, pp 125–126Google Scholar
  42. 42.
    Wen YT, Fan YY (2017) Peng w c mining of Location-Based social networks for Spatio-Temporal social Influence[M]. Advances in knowledge discovery and data miningGoogle Scholar
  43. 43.
    Yan M, Sang J, Xu C (2015) Unified YouTube Video Recommendation via Cross-network Collaboration[C]. ACM on International Conference on Multimedia Retrieval. ACM, pp 19–26Google Scholar
  44. 44.
    Zhang J, Liu B, Tang J et al (2013) Social influence locality for modeling retweeting behaviors[C]. International Joint Conference on Artificial Intelligence. AAAI press, pp 2761–2767Google Scholar
  45. 45.
    Zheng Z, Ma H, Lyu MR et al (2013) Collaborative Web Service QoS Prediction via Neighborhood Integrated Matrix Factorization[J]. IEEE Trans Serv Comput 6 (3):289–299CrossRefGoogle Scholar
  46. 46.
    Zhang J, Tang J, Li J et al (2015) Who influenced you? Predicting retweet via social influence locality[J]. ACM Trans Knowl Discov Data (TKDD) 9(3):25Google Scholar
  47. 47.
    Zhang Q, Wu J, Yang H et al (2016) Global and Local Influence-based Social Recommendation[C]. Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. ACM, pp 1917–1920Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Software EngineeringBeijing University of Posts and TelecommunicationsBeijingChina
  2. 2.School of WTO Research and EducationShanghai University of International Business and EconomicsShanghaiChina
  3. 3.State Key Laboratory of Software Development EnvironmentBeihang UniversityBeijingChina

Personalised recommendations