Skip to main content
Springer Nature Link
Log in

Review based emotion profiles for cross domain recommendation

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Several e-commerce sites are reaping the benefits of Cross-Domain Recommendation (CDR) systems to cross-sell products, guide new users and increase revenues. Current research works augment user-item ratings with a variety of auxiliary information such as location, personality, geo-tags and multimedia content that link multiple domains to provide effective CDR. In this paper, we propose a fresh perspective for generating recommendations across different domains by tapping the emotions that are encapsulated within user generated textual content such as reviews, blogs and comments. Such emotions serve as strong socio-psychological links between various entertainments domains and have the potential to obviate the cold start problems. Our CDR scheme uses an enriched emotion lexicon to analyze the emotions in online content expressed by users in the source and target domains and generates emotion-profiles of items and users in both domains. Subsequently, it applies collaborative filtering to match these profiles in order to recommend items in the target domain. We illustrate the working of our emotion-based CDR scheme using the movie and book domains as a case study. Experimental results on Movielens and Bookcrossing datasets yield 28.9% F1-measure which is a marked improvement of 71.1% as compared with a recently reported topic modeling approach to CDR for entertainment domains.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. MovieLens Dataset: http://grouplens.org/datasets/movielens/

  2. BookCrossing Dataset: http://www2.informatik.uni-freiburg.de/˜cziegler/BX/

  3. Zazie: http://www.zazie.it

  4. 4 https://code.google.com/p/ws4j

References

  1. Adomavicius G, Tuzhilin A (2005) Toward the next generation of recommender systems: a survey of the state of-the-art and possible extensions. IEEE Trans Knowl Data Eng 17:734–749. doi:10.1109/TKDE.2005.99

    Article  Google Scholar 

  2. Alderson M (2016) Connecting with audiences through character emotions. https://www.writersstore.com/connecting-with-audiences-through-character-emotions. Accessed 21 Oct 2016

  3. Aman S, Szpakowicz S (2007) Identifying expressions of emotion in text. In: International Conference on Text, Speech and Dialogue. Springer, Berlin, pp 196–205

    Google Scholar 

  4. Banerjee S, Pedersen T (2002) An adapted Lesk algorithm for word sense disambiguation using WordNet. Proc Springer Berlin Heidelberg. International Conference on Intelligent Text Processing and Computational Linguistics: pp. 136–145

  5. Bill RW, Liu Y, McInnes BT, Melton GB, Pedersen T, Pakhomov S. (2012) Evaluating semantic relatedness and similarity measures with standardized meddra queries. AMIA Annual Symposium Proc, volume 2012, page 43 American Medical Informatics Association

  6. Cantador I, Fernández-Tobías I, Berkovsky S et al (2015) Cross-domain recommender systems. In: Recommender systems handbook. Springer US, p 919–959

  7. Chakraverty S, Sharma S, Bhalla I (2015) Emotion–location mapping and analysis using twitter. Journal of Information & Knowledge Management 14(03):1550022

    Article  Google Scholar 

  8. Chiang HS, Huang TC (2015) User-adapted travel planning system for personalized schedule recommendation. Information Fusion 21:3–17

    Article  Google Scholar 

  9. Chung R, Sundaram D, Srinivasan A (2007) Integrated personal recommender systems. Proc ACM ninth international conference on Electronic commerce, p 65–74

  10. Cremonesi P, Tripodi A, Turrin R (2011) Cross-domain recommender systems. Proc 2011 I.E. 11th International Conference on Data Mining Workshops 496–503

  11. Derks T (n.d.). Filmsite Horror Films. http://www.filmsite.org/horrorfilms.html. Accessed 21 Oct 2016

  12. Ekman P (1992) An argument for basic emotions. Cognit Emot 6(3–4):169–200. doi:10.1080/02699939208411068

    Article  Google Scholar 

  13. Fernández-Tobías I, Cantador I, Kaminskas M, Ricci F (2011) A generic semantic-based framework for cross-domain recommendation. Proc of the ACM 2nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems: 25–32

  14. Fernández-Tobías I, Cantador I, Plaza L (2013) An emotion dimensional model based on social tags: Crossing folksonomies and enhancing recommendations. Proc Springer Berlin Heidelberg. International Conference on Electronic Commerce and Web Technologies, p 88–100

  15. Fernández-Tobías I, Braunhofer M, Elahi M et al (2015) Alleviating the new user problem in collaborative filtering by exploiting personality information. User Model User-Adap Inter 1–35

  16. Find me an Author (n.d.). http://www.findmeanauthor.com. Accessed 21 Oct 2016

  17. Franzoni V, Poggioni V, Zollo F (2013) Automated classification of book blurbs according to the emotional tags of the social network Zazie. In: ESSEM@ AI* IA, p 83–94

  18. Gao S, Luo H, Chen D et al (2013) Cross-domain recommendation via cluster-level latent factor model. Proc Joint European Conference on Machine Learning and Knowledge Discovery in Databases: 161–176

  19. Handel S (2011) Classification of emotions. http://www.theemotionmachine.com/classification-of-Emotions. Accessed Oct 2016

  20. Harper FM, Konstan JA (2016) The movielens datasets: history and context. ACM Transactions on Interactive Intelligent Systems (TiiS) 5(4):19. doi:10.1145/2827872

    Google Scholar 

  21. Johnson DH, Sinanovic S (2001) Symmetrizing the Kullback–Leibler ´ distance, Technical Report, Rice University

  22. Kaminskas M, Ricci F (2011) Location-adapted music recommendation using tags. Proc Springer Berlin Heidelberg. International Conference on User Modeling, Adaptation, and Personalization, p 183–194

  23. Karthik K, Ponnusamy R (2011) Adaptive machine learning approach for emotional email classification In: International Conference on Human-Computer Interaction. Springer, Berlin, pp 552–558

    Google Scholar 

  24. Kumar A, Kumar N, Hussain M, et al (2014) Semantic clustering-based cross-Domain recommendation. Proc Computational Intelligence and Data Mining (CIDM):137–141

  25. Li B, Yang Q, Xue X (2009) Transfer learning for collaborative filtering via a rating-matrix generative Model. Proc of the 26th Annual International Conference on Machine Learning: 617–624

  26. Low Y, Agarwal D, Smola AJ (2011) Multiple domain user personalization. Proc of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, p 123–131

  27. Majid A, Chen L, Chen G et al (2013) A context-aware personalized travel recommendation system based on geotagged social media data mining. Int J Geogr Inf Sci 27(4):662–684

    Article  Google Scholar 

  28. Miller GA (1995) WordNet: a lexical database for English. Commun ACM 38(11):39–41

    Article  Google Scholar 

  29. Pan W, Liu NN, Xiang, EW et al (2011) Transfer learning to predict missing ratings via heterogeneous user feedbacks. Proc International Joint Conference on Artificial Intelligence 22(3): 2318

  30. Pan W, Xiang EW, Yang Q (2012) Transfer learning in collaborative filtering with uncertain ratings. In AAAI

  31. Pazzani MJ, Billsus D (2007) Content-based recommendation systems. In: The adaptive web. Springer, Berlin, p 25–341

  32. Rawashdeh M, Alhamid MF, Alja’am JM et al (2016) Tag-based personalized recommendation in social media services. Multimedia Tools and Applications 75:13299. doi:10.1007/s11042-015-2813-0

  33. Reddy S, Inumella A, Singh N, Sangal R (2010) Hindi semantic category labeling using semantic relatedness measures. In: Proceedings of Global WordNet Conference, p 448–453

  34. Redfern N (1995) Emotion, Genre and the Hollywood Paranoid Film. https://nickredfern.wordpress.com/2009/05/07/emotion-genre-and-the-hollywood-paranoid-film/. Accessed 21 Oct 2016

  35. Resnick P, Iacovou N, Suchak M et al (1994) GroupLens: an open architecture for collaborative filtering of net news. In: Proceedings of the 1994 ACM conference on Computer supported cooperative work, p 175–186. ACM

  36. Russel JA (1980) A circumplex model of affect. J Pers Soc Psychol 39:1161–1178. doi:10.1037/h0077714

    Article  Google Scholar 

  37. Saraswat M, Chakraverty S, Mahajan N, Tokas N (2016) On using reviews and comments for cross domain recommendations and decision making. In: Computing for Sustainable Global Development (INDIACom), 2016 3rd International Conference on IEEE, p 3656–3659

  38. Schafer JB, Konstan J, Riedl J (1999) Recommender systems in e-commerce. Proc1st ACM conference on Electronic commerce p 158–166

  39. Schafer JB, Frankowski D, Herlocker J et al (2007) Collaborative filtering recommender systems. The adaptive web Springer, Berlin Heidelberg, pp 91–324

    Google Scholar 

  40. Shi Y, Larson M, Hanjalic A (2010) Mining mood-specific movie similarity with matrix factorization for context-aware recommendation. Proc of the workshop on context-aware movie recommendation, p 34–40

  41. Shi Y, Larson M, Hanjalic A (2013) Generalized tag-induced cross-domain collaborative filtering. CoRR, abs/1302:.4888. doi: 10.1145/0000000.0000000

  42. Shi Y, Larson M, Hanjalic A (2014) Collaborative filtering beyond the user-item matrix: a survey of the state of the art and future challenges. ACM Comput Surv, 47(1)

  43. Tang J, Wu S, Sun J, Su H (2012) Cross-domain collaboration recommendation. Proc of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, p 1285–1293

  44. Thayer RE (1990) The biopsychology of mood and arousal. Oxford University Press

  45. Winoto P, Tang TY (2010) The role of user mood in movie recommendations. Expert Syst Appl 37(8):6086–6092

    Article  Google Scholar 

  46. Yang YH, Lin YC, Su YF, Chen HH (2007) Music emotion classification: a regression approach. In: 2007 I.E. International Conference on Multimedia and Expo, p 208–211

  47. Zhang D, He T, Liu Y et al (2014) A carpooling recommendation system for taxicab services. IEEE Transactions on Emerging Topics in Computing 2(3):254–266

    Article  Google Scholar 

  48. Ziegler CN, McNee SM, Konstan JA et al (2005) Improving recommendation lists through Topic diversification. Proc in ACM 14th international conference on World Wide Web, p 22–32

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Netaji Subhas Institute of Technology, Delhi, India

    Shampa Chakraverty & Mala Saraswat

Authors
  1. Shampa Chakraverty
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mala Saraswat
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Mala Saraswat.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chakraverty, S., Saraswat, M. Review based emotion profiles for cross domain recommendation. Multimed Tools Appl 76, 25827–25850 (2017). https://doi.org/10.1007/s11042-017-4767-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-017-4767-x

Keywords