Advertisement

A fine-grained social network recommender system

  • Markos Aivazoglou
  • Antonios O. Roussos
  • Dionisis Margaris
  • Costas Vassilakis
  • Sotiris Ioannidis
  • Jason Polakis
  • Dimitris SpiliotopoulosEmail author
Original Article
  • 67 Downloads

Abstract

Recommender systems have greatly evolved in recent years and have become an integral part of the Web. From e-commerce sites to mobile apps, our daily routine revolves around a series of “small” decisions that are influenced by such recommendations. In a similar manner, online social networks recommend only a subset of the massive amount of content published by a user’s friends. However, the prevalent approach for the content selection process in such systems is driven by the amount of interaction between the user and the friend who published the content. As a result, content of interest is often lost due to weak social ties. In this paper, we present a fine-grained recommender system for social ecosystems, designed to recommend media content (e.g., music videos, online clips) published by the user’s friends. The system design was driven by the findings of our qualitative user study that explored the value and requirements of a recommendation component within a social network. The core idea behind the proposed approach was to leverage the abundance of preexisting information in each user’s account for creating interest profiles, to calculate similarity scores at a fine-grained level for each friend. The intuition behind the proposed method was to find consistent ways to obtain information representations that can identify overlapping interests in very specific sub-categories (e.g., two users’ music preferences may only coincide on hard rock). While the system is intended as a component of the social networking service, we developed a proof-of-concept implementation for Facebook and explored the effectiveness of our underlying mechanisms for content analysis. Our experimental evaluation demonstrates the effectiveness of our approach, as the recommended content of interest was both overlooked by the existing Facebook engine and not contained in the users’ Facebook News Feed. We also conducted a user study for exploring the usability aspects of the prototype and found that it offers functionality that could significantly improve user experience in popular services.

Keywords

Social networks Recommender systems Content analysis Interest profiles Usability 

Notes

References

  1. Aivazoglou M, Roussos O, Ioannidis S, Spiliotopoulos D, Polakis J (2017) Reveal: fine grained recommendations in online social networks. In: Proceedings of the 2017 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM 2017), Sydney, pp 1–4Google Scholar
  2. Antonakaki D, Spiliotopoulos D, Samaras CV, Pratikakis P, Ioannidis S, Fragopoulou P (2017) Social media analysis during political turbulence. PLoS ONE 12(10):1–23CrossRefGoogle Scholar
  3. Bakshy E, Eckles D, Yan R, Rosenn I (2012) Social influence in social advertising: evidence from field experiments. In: Proceedings of the 13th ACM conference on electronic commerce, Valencia, pp 146–161Google Scholar
  4. Berkovsky S, Freyne J (2015) Web personalization and recommender systems. In: Proceedings of the 21st ACM SIGKDD international conference on knowledge discovery and data mining, Sydney, pp 2307–2308Google Scholar
  5. Bird S, Loper E, Klein E (2009) Natural language processing with Python. O’Reilly Media Inc, SebastopolzbMATHGoogle Scholar
  6. Cai X, Bain M, Krzywicki A, Wobcke W, Sok Y, Compton P, Mahidadia A (2010) Collaborative filtering for people to people recommendation in social networks. In: Advances in artificial intelligence. Lecture notes in computer science, vol 6464, pp 476–485CrossRefGoogle Scholar
  7. Camacho L, Alves-Souza SΝ (2018) Social network data to alleviate cold-start in recommender system: a systematic review. Inf Process Manag 54(4):529–544CrossRefGoogle Scholar
  8. Chamoso P, Rivas A, Rodríguez S, Bajo J (2018) Relationship recommender system in a business and employment-oriented social network. Inf Sci 433:204–220CrossRefGoogle Scholar
  9. Chin J, Diehl V, Norman K (1988) Development of an instrument measuring user satisfaction of human-computer interface. In: Proceedings of the ‘88 SIGCHI conference on human factors in computing systems, Washington, DC, pp 213–218Google Scholar
  10. Contratres FG, Alves-Souza SN, Filgueiras L, DeSouza L (2018) Sentiment analysis of social network data for cold-start relief in recommender systems. In: Proceedings of the 2018 conference on information systems and technologies, Naples, pp 122–132Google Scholar
  11. Da’u A, Salim N, Rabiu I, Osman A (2020) Weighted aspect-based opinion mining using deep learning for recommender system. Expert Syst Appl 140:112871CrossRefGoogle Scholar
  12. De Meo P, Fotia L, Messina F, Rosaci D, Sarné GM (2018) Providing recommendations in social networks by integrating local and global reputation. Inf Syst 78:58–67CrossRefGoogle Scholar
  13. De Pessemier T, Dooms S, Roelandts J, Martens L (2011) Analysis of the information value of user connections for video recommendations in a social network. In: Proceedings of the 2011 CEUR workshop, Pisa, pp 1–7Google Scholar
  14. Dridi A, Reforgiato Recupero D (2019) Leveraging semantics for sentiment polarity detection in social media. Int J Mach Learn Cybern 10:2045CrossRefGoogle Scholar
  15. Facebook (2017) Graph API edges. https://goo.gl/PdWuYm. Accessed 11 Oct 2018
  16. Facebook (2018) Using actions. https://goo.gl/9schoS. Accessed 15 Oct 2018
  17. Facebook (2019) Facebook—how does news feed decide which stories to show? https://goo.gl/Dupvg8. Accessed 20 Oct 2019
  18. Facebook news feed (2016) News Feed FYI: a window into news feed. https://goo.gl/ByPLgF. Accessed 19 Oct 2018
  19. Fang X, Zhan J (2015) Sentiment analysis using product review data. J Big Data 2(1):1–14CrossRefGoogle Scholar
  20. Freebase (2018) A community-curated database of well-known people, places, and things. https://developers.google.com/freebase/. Accessed 11 Nov 2018
  21. Garosi F (2008) PyCLIPS Manual. http://pyclips.sourceforge.net/manual/pyclips.html. Accessed 11 Mar 2019
  22. Gretarsson B, O’Donovan J, Bostandjiev S, Hall C, Holerer T (2010) Smallworlds: visualizing social recommendations. Comput Graph Forum 29(3):833–842CrossRefGoogle Scholar
  23. Guy I, Zwerdling N, Ronen I, Carmel D, Uziel E (2010) Social media recommendation based on people and tags. In: Proceedings of the 33rd international ACM SIGIR conference on research and development in information retrieval (SIGIR’10), New York, NY, pp 194–201Google Scholar
  24. He J, Chu WW (2010) A social network-based recommender system (SNRS). Ann Inf Syst 12:47–74CrossRefGoogle Scholar
  25. Horn L (1989) A natural history of negation. University of Chicago Press, ChicagoGoogle Scholar
  26. Jones AM, Arya A, Agarwal P, Gaurav P, Arya T (2017) An ontological sub-matrix factorization based approach for cold-start issue in recommender systems. In: Proceedings of the 2017 international conference on current trends in computer, electrical, electronics and communication, Mysore, India, pp 161–166Google Scholar
  27. Kalaï A, Zayani CA, Amous I, Abdelghani W, Sèdes F (2018) Social collaborative service recommendation approach based on user’s trust and domain-specific expertise. Fut Gen Comput Syst 80:355–367CrossRefGoogle Scholar
  28. Li J, Yang Y (2018) Recommender systems based on opinion mining and deep neural networks. In: MATEC web of conferences, 173, Article 03016CrossRefGoogle Scholar
  29. Liu B (2015) Sentiment analysis: mining opinions, sentiments, and emotions. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  30. Ma X, Ma J, Li H, Jiang Q, Gao S (2018) ARMOR: a trust-based privacy-preserving framework for decentralized friend recommendation in online social networks. Fut Gen Comput Syst 79:82–94CrossRefGoogle Scholar
  31. Makki R, Soto AJ, Brooks S, Milios E (2016) Twitter message recommendation based on user interest profiles. In: Proceedings of the 2016 IEEE/ACM international conference on advances in social networks analysis and mining, San Francisco, pp 406–410Google Scholar
  32. Margaris D, Vassilakis C (2018) Exploiting rating abstention intervals for addressing concept drift in social network recommender systems. Inf Multidiscip Digit Publ Inst 10(7), Article 230Google Scholar
  33. Margaris D, Vassilakis C, Georgiadis P (2016) Recommendation information diffusion in social networks considering user influence and semantics. Soc Netw Anal Min 6(108):1–22Google Scholar
  34. Margaris D, Vassilakis C, Georgiadis P (2018) Query personalization using social network information and collaborative filtering techniques. Fut Gen Comput Syst 78(1):440–450CrossRefGoogle Scholar
  35. Margaris D, Spiliotopoulos D, Vassilakis C (2019) Social relations versus near neighbours: reliable recommenders in Limited Information Social Network Collaborative Filtering for online advertising. In: Proceedings of the 2019 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM 2019), Vancouver, pp 1–8Google Scholar
  36. Mohammadi SA, Andalib A (2017) Using the opinion leaders in social networks to improve the cold start challenge in recommender systems. In: Proceedings of the 3rd IEEE international conference on web research, Tehran, pp 62–66Google Scholar
  37. Nazir F, Ghazanfar MA, Maqsood M, Aadil F, Rho S, Mehmood I (2019) Social media signal detection using tweets volume, hashtag, and sentiment analysis. Multimedia Tools Appl 78:3553CrossRefGoogle Scholar
  38. Pasricha H, Solanki S (2019) A New Approach for Book Recommendation Using Opinion Leader Mining. Emerging Research in Electronics, Computer Science and Technology, Springer-Singapore, pp 501–515Google Scholar
  39. Polanyi L, Zaenen A (2006) Contextual valence shifters. Comput Attitude Affect Text Theory Appl 20:1–10CrossRefGoogle Scholar
  40. Reshma R, Ambikesh G, Thilagam P (2016) Alleviating data sparsity and cold start in recommender systems using social behaviour. Proceedings of the 2016 international conference on recent trends in information technology, New Jersey, pp 1–8Google Scholar
  41. Sanders N (2011) Twitter sentiment corpus. https://github.com/zfz/twitter_corpus. Accessed 5 Dec 2019
  42. Sangeetha J, Prakash V (2019) Improved Feature-Specific Collaborative Filtering Model for the Aspect-Opinion Based Product Recommendation. Advances in Big Data and Cloud Computing, Springer-Singapore, pp 275–289Google Scholar
  43. Sauri R (2008) A factuality profiler for eventualities in text. PhD dissertation, Brandeis UniversityGoogle Scholar
  44. Shen RP, Zhang HR, Yu H, Min F (2019) Sentiment based matrix factorization with reliability for recommendation. Expert Syst Appl 135:249–258CrossRefGoogle Scholar
  45. Taboada M, Brooke J, Tofiloski M, Voll K, Stede M (2011) Lexicon based methods for sentiment analysis. Comput Linguist Arch 37(2):267–307CrossRefGoogle Scholar
  46. Tewari AS, Jain R, Singh JP, Barman AG (2019) Personalized product recommendation using aspect-based opinion mining of reviews. In: Proceedings of the international ethical hacking conference 2018, Kolkata, India, pp 443–453Google Scholar
  47. Twitter (2019) Twitter social network homepage. https://twitter.com/. Accessed 11 Mar 2019
  48. Urban dictionary (2019) http://www.urbandictionary.com/. Accessed 25 Oct 2019
  49. Viswanath B, Mislove A, Cha M, Gummadi KP (2009) On the evolution of user interaction in facebook. In: Proceedings of the 2nd ACM workshop on online social networks, Barcelona, pp 37–42Google Scholar
  50. Wang F, Jiang W, Li X, Wang G (2018) Maximizing positive influence spread in online social networks via fluid dynamics. Fut Gen Comput Syst 86:1491–1502CrossRefGoogle Scholar
  51. Wilson C, Sala A, Puttaswamy KP, Zhao BY (2012) Beyond social graphs: user interactions in online social networks and their implications. ACM Trans Web 6(4):1–31CrossRefGoogle Scholar
  52. Wired (2013) Why Facebook is teaching its machines to think like humans. https://goo.gl/wk365x. Accessed 5 Dec 2018
  53. Zhang K, Cheng Y, Xie Y, Honbo D, Agrawal A, Palsetia D, Lee K, Liao WK, Choudhary A (2015) Ses: sentiment elicitation system for social media data. In: Proceedings of the 11th international conference on data mining, Las Vegas, pp 1–11Google Scholar
  54. Zhang Q, Wu J, Zhang Q, Zhang P, Long G, Zhang C (2018) Dual influence embedded social recommendation. World Wide Web 21(4):849–874CrossRefGoogle Scholar
  55. Zheng X, Luo Y, Sun L, Zhang J, Chen F (2018) A tourism destination recommender system using users’ sentiment and temporal dynamics. J Intell Inf Syst 51(3):557–578CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Austria, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Institute of Computer ScienceFoundation for Research and TechnologyIraklioGreece
  2. 2.Department of Informatics and TelecommunicationsUniversity of AthensAthensGreece
  3. 3.Department of Informatics and TelecommunicationsUniversity of the PeloponneseTripoliGreece
  4. 4.Computer Science DepartmentUniversity of Illinois at ChicagoChicagoUSA

Personalised recommendations