Advertisement

Analysing Emotional Sentiment in People’s YouTube Channel Comments

  • Eleanor MulhollandEmail author
  • Paul Mc Kevitt
  • Tom Lunney
  • Karl-Michael Schneider
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 196)

Abstract

Online recommender systems are useful for media asset management where they select the best content from a set of media assets. We are developing a recommender system called 360-MAM-Select for educational video content. 360-MAM-Select utilises sentiment analysis, emotion modeling and gamification techniques applied to people’s comments on videos, for the recommendation of media assets. Here, we discuss the architecture of 360-MAM-Select, including its sentiment analysis module, 360-MAM-Affect and gamification module, 360-Gamify. 360-MAM-Affect is implemented with the YouTube API [9], GATE [5] for natural language processing, EmoSenticNet [8] for identifying emotion words and RapidMiner [20] to count the average frequency of emotion words identified. 360-MAM-Affect is tested by tagging comments on the YouTube channels, Brit Lab/Head Squeeze [3], YouTube EDU [28], Sam Pepper [22] and MyTop100Videos [18] with EmoSenticNet [8] in order to identify emotional sentiment. Our results show that Sad, Surprise and Joy are the most frequent emotions across all the YouTube channel comments. Future work includes further implementation and testing of 360-MAM-Select deploying the Unifying Framework [25] and Emotion-Imbued Choice (EIC) model [13] within 360-MAM-Affect for emotion modelling, by collecting emotion feedback and sentiment from users when they interact with media content. Future work also includes implementation of the gamification module, 360-Gamify, in order to check its suitability for improving user participation with the Octalysis gamification framework [4].

Keywords

360-MAM-Affect 360-MAM-Select Affective computing Brit Lab EmoSenticNet Gamification Google YouTube API Head Squeeze Machine learning Natural language processing Recommender system Sentiment analysis YouTube YouTube EDU 

Notes

Acknowledgments

We wish to thank Dr. Brian Bridges, Dr. Kevin Curran and Dr. Lisa Fitzpatrick at Ulster University, John Farren and Judy Wilson at 360 Production Ltd. and Alleycats TV for their useful suggestions on this work. This research is funded by a Northern Ireland Department of Employment & Learning (DEL) Co-operative Awards in Science & Technology (CAST) Ph.D. Studentship Awardat Ulster University.

References

  1. 1.
    Bing, L.: AI and opinion mining. IEEE Intell. Syst. 25(3), 76–80 (2010)Google Scholar
  2. 2.
    Blair, O.: Sam pepper heavily criticised for vile fake murder prank video. http://www.independent.co.uk/news/people/sam-pepper-criticised-over-vile-prank-fake-murder-video-a6754861.html. Accessed 15 Dec 2015
  3. 3.
    Brit Lab/Head Squeeze.: 360 Production. https://www.youtube.com/user/HeadsqueezeTV. Accessed 15 Dec 2015
  4. 4.
    Chou, Y.K.: Actionable Gamification: Beyond Points, Badges, and Leaderboards. Leanpub, Fremont (2015)Google Scholar
  5. 5.
    Cunningham, H.: General Architecture for Text Engineering (GATE). https://gate.ac.uk/. Accessed 10 Dec 2015
  6. 6.
    Downes, G., McKevitt, P., Lunney, T., Farren, J., Ross, C.: 360-PlayLearn: gamification and game-based learning for virtual learning environments on interactive television. In: Walshe, R., Perrin, D., Cunningham, P. (eds.) Proceedings of the 23rd Irish Conference on Artificial Intelligence and Cognitive Science (AICS-2012), Carlton Hotel, Dublin Airport, Dublin, Ireland, 17–19 September 2012, pp. 116–121. Logos Verlag, Berlin (2012)Google Scholar
  7. 7.
    Faridani, S.: Using canonical correlation analysis for generalized sentiment analysis, product recommendation and search. In: Proceedings of the Fifth ACM Conference on Recommender Systems, Chicago, Illinois, USA, 23–27 October, pp. 355–358 (2011)Google Scholar
  8. 8.
    Gelbukh, A.: EmoSenticNet. http://www.gelbukh.com/emosenticnet/. Accessed 20 Feb 2014
  9. 9.
    Google: YouTube API: Google Developer’s Guide. https://developers.google.com/youtube/. Accessed 17 Nov 2015
  10. 10.
    Hanser, E., McKevitt, P., Lunney, T., Condell, J.: NewsViz: emotional visualization of news stories. In: Inkpen, D., Strapparava, C. (eds.) Proceedings of the NAACL-HLT Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, Millennium Biltmore Hotel, Los Angeles, CA, USA, 5 June, pp. 125–130 (2010)Google Scholar
  11. 11.
    Kant, V., Bharadwaj, K.K.: Integrating collaborative and reclusive methods for effective recommendations: a fuzzy Bayesian approach. Int. J. Intell. Syst. 28(11), 1099–1123 (2013)CrossRefGoogle Scholar
  12. 12.
    Khan, K., Baharudin, B.B., Khan, A., e-Malik, F.: Mining opinion from text documents: a survey. In: Proceedings of the 3rd IEEE International Conference on Digital Ecosystems and Technologies, Istanbul, Turkey, 1–3 June, pp. 217–222 (2009)Google Scholar
  13. 13.
    Lerner, J.S., Li, Y., Valdesolo, P., Kassam, K.: Emotion and decision making. Annu. Rev. Psychol. 66, 799–823 (2015). (Supplemental Materials)CrossRefGoogle Scholar
  14. 14.
    Linden, G., Smith, B., York, J.: Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Comput. 7(1), 76–80 (2003)CrossRefGoogle Scholar
  15. 15.
    Martin, B.: 2015 UK Digital Future in Focus (whitepaper). 2015 Digital Future in Focus. https://www.comscore.com/Insights/Blog/2015-Europe-Digital-Future-in-Focus. Accessed 17 Dec 2015
  16. 16.
    Mayer, J.D., Gaschke, Y.N.: The experience and meta-experience of mood. J. Pers. Soc. Psychol. 55(1), 102–111 (1988)CrossRefGoogle Scholar
  17. 17.
    Mulholland, E., McKevitt, P., Lunney, T., Farren, J., Wilson, J.: 360-MAM-Affect: sentiment analysis with the Google prediction API and EmoSenticNet. In: Proceedings of the 7th International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN-2015), Politecnico di Torino, Turin (Torino), Italy, 10–12 June, pp. 1–5 (2015)Google Scholar
  18. 18.
    MyTop10Videos: MyTop100Videos. https://www.youtube.com/user/MyTop10Videos. Accessed 15 Dec 2015
  19. 19.
    Nasukawa, T., Yi, J.: Sentiment analysis: capturing favourability using natural language processing. In: Proceedings of the 2nd International Conference on Knowledge Capture, Sanibel Island, FL, USA, 23–25 October, pp. 70–77 (2003)Google Scholar
  20. 20.
    RapidMiner: RapidMiner. https://rapidminer.com/. Accessed 4 May 2015
  21. 21.
    Ricci, F., Rokach, L., Shapira, B.: Recommender Systems Handbook. Springer Press, New York (2011)CrossRefzbMATHGoogle Scholar
  22. 22.
    Sam Pepper: Sam. https://www.youtube.com/user/OFFICIALsampepper. Accessed 15 Dec 2015
  23. 23.
    Śnieżyński, B.: Recommendation system using multistrategy inference and learning. In: Niewiadomski, A., Kacprzyk, J., Szczepaniak, P.S. (eds.) Advances in Web Intelligence, pp. 421–426. Springer, Berlin (2005)Google Scholar
  24. 24.
    Strapparava, C., Valitutti, A.: WordNet-Affect: an affective extension of WordNet. In: Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC 2004), Lisbon, Portugal, 26–28 May, pp. 1083–1086 (2004)Google Scholar
  25. 25.
    Tkalčič, M., Košir, A., Tasič, J.: Affective recommender systems: the role of emotions in recommender systems. In: Proceedings of the RecSys 2011 Workshop Human Decision Making in Recommender Systems (Decisions@RecSys 2011), Chicago, Illinois, 23–27 October, pp. 9–13 (2011)Google Scholar
  26. 26.
    Tzanis, G., Katakis, I., Partalas, I., Vlahavas, I.: Modern applications of machine learning. In: Proceedings of the 1st Annual SEERC Doctoral Student Conference – DSC 2006, 1(1), Thessaloniki, Greece, 10 July, pp. 1–10 (2006)Google Scholar
  27. 27.
    Wilson, T., Wiebe, J., Hoffmann, P.: Recognising contextual polarity in phrase-level sentiment analysis. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT 2005), Vancouver, British Columbia, Canada, 6–8 October, pp. 347–354 (2005)Google Scholar
  28. 28.
    YouTube EDU: YouTube EDU. https://www.youtube.com/channel/UC3yA8nDwraeOfnYfBWun83g. Accessed 15 Dec 2015
  29. 29.
    YouTube: YouTube Statistics. http://www.youtube.com/yt/press/statistics.html. Accessed 17 Mar 2015
  30. 30.
    Zheng, Y., Burke, R., Mobasher, B.: The role of emotions in context-aware recommendation. In: Proceedings of the 3rd International Workshop on Human Decision Making in Recommender Systems, ACM, Hong Kong, China, 12 October, pp. 21–28 (2013)Google Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2017

Authors and Affiliations

  • Eleanor Mulholland
    • 1
    Email author
  • Paul Mc Kevitt
    • 1
  • Tom Lunney
    • 1
  • Karl-Michael Schneider
    • 2
  1. 1.School of Creative Arts and TechnologiesUlster UniversityDerry/LondonderryNorthern Ireland, UK
  2. 2.Google Ireland Ltd.DublinIreland

Personalised recommendations