Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Related Work
Methodology
Overview of the Tweets Affective Classifier Model
Overview of Comparative Platform for Recommenders
Datasets
Limitations
Future Work
References
All Topics
Computer Science
Machine Learning

Text-based Emotion Aware Recommender

Profile image of William G KennedyWilliam G Kennedy

2020, Computer Science & Information Technology

https://doi.org/10.5121/CSIT.2020.101009
visibility

…

description

14 pages

link

2 files

Abstract

We apply the concept of users' emotion vectors (UVECs) and movies' emotion vectors (MVECs) as building components of Emotion Aware Recommender System. We built a comparative platform that consists of five recommenders based on content-based and collaborative filtering algorithms. We employed a Tweets Affective Classifier to classify movies' emotion profiles through movie overviews. We construct MVECs from the movie emotion profiles. We track users' movie watching history to formulate UVECs by taking the average of all the MVECs from all the movies a user has watched. With the MVECs, we built an Emotion Aware Recommender as one of the comparative platforms' algorithms. We evaluated the top-N recommendation lists generated by these Recommenders and found the top-N list of Emotion Aware Recommender showed serendipity recommendations.

Related papers

A Proposed Movie Recommendation Method Using Emotional Word Selection
Juhyun Eune

Many online movie sites or music sites offering recommendation services employ a collaborative filtering technique archived by analyzing customers' satisfaction rating, evaluation, search history, download records etc. This approach, however, has difficulty with reflecting individuals' perosonalities and their own taste for the recommendation. Exploiting such emotional data to a film recommendation remains a challenge in the present. To solve this, we propose an emotion words selection method usable for the collaborative filtering. Through the proposed emotion-based collaborative filtering method, a recommendation system can exploit individuals' emotional differences on the movie items for the recommendation process. This approach was proven by gathering users' emotion words selection and satisfaction rating data on several films, and comparing them with MBTI (Myers-Briggs Type Indicator) that is a representative psychometric test for measuring psychological preferences and personalities. This study assumes that individual's movie taste is much related to the personalities classifiable by MBTI types, because movie taste and evaluation on a movie is influenced by individual's subjective matters. The results of this study show that emotion words based collaborative filtering method is appropriate for extracting users' MBTI types. Thus, if a recommendation service offers users films based on their MBTI types, the users can be recommended more customized films.

View PDFchevron_right
Affective recommender systems: the role of emotions in recommender
Jurij Tasič

2013

Recommender systems have traditionally relied on data-centric descriptors for content and user modeling. In recent years we have witnessed an increasing number of attempts to use emotions in di↵erent ways to improve the quality of recommender systems. In this paper we introduce a unifying framework that positions the research work, that has been done so far in a scattered manner, in a three stage model. We provide examples of research that cover various aspects of the detection of emotions and the inclusion of emotions into recommender systems.

View PDFchevron_right
Affective recommender systems: the role of emotions in recommender systems
Andrej Košir

2011

Recommender systems have traditionally relied on data-centric descriptors for content and user modeling. In recent years we have witnessed an increasing number of attempts to use emotions in different ways to improve the quality of recommender systems. In this paper we introduce a unifying framework that positions the research work, that has been done so far in a scattered manner, in a three stage model. We provide examples of research that cover various aspects of the detection of emotions and the inclusion of emotions into ...

View PDFchevron_right
Emotion-Based Recommender System for Overcoming the Problem of Information Overload
Hernani Costa, Luis Macedo

Highlights on Practical Applications of Agents and Multi-Agent Systems, 2013

"Nowadays, we are experiencing a huge growth in the available information, caused by the advent of communication technology, which humans cannot handle by themselves. Personal Assistant Agents can help humans to cope with the task of selecting the relevant information. In order to perform well, these agents should consider not only their preferences, but also their mental states (such as beliefs, intentions and emotions) when recommending information. In this paper, we describe an ongoing Recommender System application, that implements a Multiagent System, with the purpose of gathering heterogeneous information from different sources and selectively deliver it based on: user's preferences; the community's trends; and on the emotions that it elicits in the user."

View PDFchevron_right
An Effective Movie Recommendation System Using Collaborative Filtering and User Review Sentimental Analysis (UGC Care list Journal)
BRIJESHKUMAR Y . PANCHAL

Asian publication corporation sahibabad (india) , 2022

In the present advanced world, a suggestion/recommendation engine is quite possibly the most incredible asset for showcasing. A recommender system is only a data separating system made out of machine learning algorithms that foresee a given client's evaluations or inclinations for a thing. A proposal engine assists with tending to the test of data over-burden in the internet business space. Accordingly, it can help in saving a ton of perusing time for clients, as the recommendation system guides the client to results of the things which he is destined to like. Its customized highlights improve client commitment and maintenance. The possibility of proposal engine is likewise something you are as of now acquainted with; whether it is item suggestions on Amazon, film suggestions on Netflix, or music ideas on YouTube, recommender frameworks are now supporting numerous parts of your experience on the web.

View PDFchevron_right
Usage of affective computing in recommender systems
Jurij Tasič

ELEKTROTEHNIˇSKI VESTNIK, 2011

Abstract. In this paper we present the results of three investigations of our broad research on the usage of affect and personality in recommender systems. We improved the accuracy of a content-based recommender system with the inclusion of affective parameters in user and item modeling. We improved the accuracy of a content filtering recommender system under the cold start conditions with the introduction of a personality-based user similarity measure. Furthermore we developed a system for implicit tagging of images with affective metadata. ...

View PDFchevron_right
Recent developments in affective recommender systems
Rahul Katarya

• We considered five investigation & analysis questions (IAs) for affective recommender systems. • We categorized affective recommendation systems as: techniques, data sets, nature, methods and platform. • We also incorporated according to information and evaluation techniques. • Research articles published between years 2003 to February 2016 are taken into account. a b s t r a c t Recommender systems (RSs) are playing a significant role since 1990s as they provide relevant, personalized information to the users over the internet. Lots of work have been done in information filtering, utilization, and application related to RS. However, an important area recently draws our attention which is affective recommender system. Affective recommender system (ARS) is latest trending area of research, as publication in this domain are few and recently published. ARS is associated with human behaviour, human factors, mood, senses, emotions, facial expressions, body gesture and physiological with human–computer interaction (HCI). Due to this assortment and various interests, more explanation is required, as it is in premature phase and growing as compared to other fields. So we have done literature review (LR) in the affective recommender systems by doing classification, incorporate reputed articles published from the year 2003 to February 2016. We include articles which highlight, analyse, and perform a study on affective recommender systems. This article categorizes, synthesizes, and discusses the research and development in ARS. We have classified and managed ARS papers according to different perspectives: research gaps, nature, algorithm or method adopted, datasets, the platform on executed, types of information and evaluation techniques applied. The researchers and professionals will positively support this survey article for understanding the current position, research in affective recommender systems and will guide future trends, opportunity and research focus in ARS.

View PDFchevron_right
Emotion Based Recommendation System for Various Applications
Priya Dharshini

International Journal of Advance Research and Innovative Ideas in Education, 2019

Most of the existing systems are highly complex in terms of time and storage for recognizing user behavior. This paper proposes an emotion based recommendation system for various applications that learns the emotions of the user from the camera. The human face acts as an important part in an individual’s body and helps in detection of one’s mood. The extracted input undergoes face detection, feature extraction, emotion recognition and application identification. The application includes playing music, videos, providing motivational quotes. This eliminates the time consuming and tedious task of manually segregating a playlist or searching for motivational quotes and videos. The experimental results are obtained by classifying the emotions using convolutional neural networks and support vector machine. The data are validated using testing and training method to obtain the exact emotion of the user. The applications are identified from the predicted emotions. By this way the emotions a...

View PDFchevron_right
Leveraging Emotion Features in News Recommendations
nastaran babanejad

2019

Online news reading has become very popular as the web provides access to news articles from millions of sources around the world. As a specific application domain, news recommender systems aim to give the most relevant news article recommendations to users according to their personal interests and preferences. Recently, a family of models has emerged that aims to improve recommendations by adapting to the contextual situation of users. These models provide the premise of being more accurate as they are tailored to satisfy the continuously changing needs of users. However, little attention has been paid to the emotional context and its potential on improving the accuracy of news recommendations. The main objective of this paper is to investigate whether, how and to what extent emotion features can improve recommendations. Towards that end, we derive a large number of emotion features that can be attributed to both items and users in the domain of news. Then, we devise state-of-the-a...

View PDFchevron_right
Affective Recommendation of Movies Based on Selected Connotative Features
Riccardo Leonardi

IEEE Transactions on Circuits and Systems for Video Technology, 2013

The apparent difficulty in assessing emotions elicited by movies and the undeniable high variability in subjects' emotional responses to film content have been recently tackled by exploring film connotative properties: the set of shooting and editing conventions that help in transmitting meaning to the audience. Connotation provides an intermediate representation that exploits the objectivity of audiovisual descriptors to predict the subjective emotional reaction of single users. This is done without the need of registering users' physiological signals. It is not done by employing other people's highly variable emotional rates, but by relying on the intersubjectivity of connotative concepts and on the knowledge of user's reactions to similar stimuli. This paper extends previous work by extracting audiovisual and film grammar descriptors and, driven by users' rates on connotative properties, creates a shared framework where movie scenes are placed, compared, and recommended according to connotation. We evaluate the potential of the proposed system by asking users to assess the ability of connotation in suggesting film content able to target their affective requests.

View PDFchevron_right

References (53)

  1. 3389 Let's Get Harry (1986) 35 3999 Vertical Limit (2000) 36 4367 Lara Croft: Tomb Raider (2001) 37 5088 Going Places (Valseuses, Les) (1974) 38 5244 Shogun Assassin (1980) 39 5540 Clash of the Titans (1981) 40 5667 Tuck Everlasting (2002) 41 6911 Jolson Story, The (1946) 42 7132 Night at the Opera, A (1935) 43 7248 Suriyothai (a.k.a. Legend of Suriyothai, The) (2001) 44 7302 Thief of Bagdad, The (1924) 45 7925 Hidden Fortress, The (Kakushi-toride no san-akunin) (1958) 46 25946 Three Musketeers, The (1948) 47 31923 Three Musketeers, The (1973) 48 43556 Annapolis (2006)
  2. 48394 Pan's Labyrinth (Laberinto del fauno, El) (2006) 50 50003 DOA: Dead or Alive (2006)
  3. 95441 Ted (2012) 54 96530 Conception (2011) 55 106920 Her (2013) 56 112175 How to Train Your Dragon 2 (2014) 57 112911 Hercules (2014) 58 115713 Ex Machina (2015) 59 115727 Crippled Avengers (Can que) (Return of the 5 Deadly Venoms) (1981) 60 122918 Guardians of the Galaxy 2 (2017) 61 131714 Last Knights (2015) 62 134775 Dragon Blade (2015) 63 147662 Return of the One-Armed Swordsman (1969) 64 149406 Kung Fu Panda 3 (2016) 65 160563 The Legend of Tarzan (2016)
  4. CONCLUSION Leverage on our prior work in affective computing [1] that making use of the Tweets Affective Classifier (TAC) to generate our needed movie emotion labeled dataset; we demonstrated in this paper a method to build an Emotion Aware Recommender (EAR) with intriguing results. We developed a Recommender platform using the following Recommender algorithms: Item-based Collaborative Filtering (IBCF), User-based Collaborative Filtering (UBCF), Content-based movie Genres Aware Recommender (GAR), Content-based Emotion Aware Recommender (EAR), and Content-based Multi-channel Emotion Aware Recommender (MAR). With each Recommender algorithm, we generate a top-20 recommendation list. We randomly selected user id 400 as an active user for testing. We compute the emotion profile, wvec, for the test user. Using the test user's wvec and the list of ivec from each of the top-20 list, we computed the top-5 for each top-20 list generated by the Recommenders. The top-N list made by each Recommender is unique, with few overlaps among the lists. We have a total of 100 movies in the combined top- 20 lists. We found 35 duplicated films among the top-20 recommendation lists. The top-N list made by each Recommender met its design focus. For example, GAR correctly recommended movies that meet the active test user's genre taste. EAR, on the other hand, shows intrigue results. We believe that with further investigation, we could enhance EAR to make serendipity recommendations. REFERENCES
  5. Leung, John Kalung, Griva, Igor & Kennedy, William G., (2020) "Making Use of Affective Features from Media Content Metadata for Better Movie Recommendation Making", Preprint at https://arxiv.org/abs/2007.00636.
  6. Wang, Yibo, Wang, Mingming & Xu, Wei, (2018) "A sentiment-enhanced hybrid recommender system for movie recommendation: a big data analytics framework", Wireless Communications and Mobile Computing.
  7. Wang, Wei & Wang, Hongwei, (2015) "Opinion-enhanced collaborative filtering for recommender systems through sentiment analysis", New Review of Hypermedia and Multimedia, Vol, 21, No. (3- 4), pp278-300.
  8. Kumar, Gaurav, (2018) "A multi-criteria decision making approach for recommending a product using sentiment analysis", In 2018 12th International Conference on Research Challenges in Information Science (RCIS), IEEE, pp1-6.
  9. Katarya, Rahul & Verma, Om Prakash, (2016) "Recent developments in affective recommender systems",Physica A: Statistical Mechanics and its Applications, Vol. 461, pp182-190.
  10. Mizgajski, Jan & Morzy, Miko\laj, (2019) "Affective recommender systems in online news industry: how emotions influence reading choices", User Modeling and User-Adapted Interaction, Vol. 29, Springer,pp345-379.
  11. Haruna, Khalid, Akmar Ismail, Maizatul, Suhendroyono, Suhendroyono, Damiasih, Damiasih, Pierewan, Adi Cilik, Chiroma, Haruna & Herawan, Tutut, (2017) "Context-aware recommender system: A review of recent developmental process and future research direction", Applied Sciences, Vol. 7 No. 12, pp1211.
  12. Tkalčič, Marko, Burnik, Urban, Odić, Ante, Košir, Andrej & Tasič, Jurij, (2012) "Emotion-aware recommender systems-a framework and a case study", In International Conference on ICT Innovations, Springer, pp141-150.
  13. Qian, Yongfeng, Zhang, Yin, Ma, Xiao, Yu, Han & Peng. Limei, (2019) "EARS: Emotion-aware recommender system based on hybrid information fusion", Information Fusion, Elsevier, Vol. 46, pp141-146.
  14. Orellana-Rodriguez, Claudia, Diaz-Aviles, Ernesto & Nejdl, Wolfgang, (2015) "Mining affective context in short films for emotion-aware recommendation", In Proceedings of the 26th ACM Conference on Hypertext & Social Media, pp185-194.
  15. Sundermann, Camila Vaccari, Domingues, Marcos Aurélio, Sinoara, Roberta Akemi, Marcacini, Ricardo Marcondes & Rezende, Solange Oliveira, (2019) "Using opinion mining in context-aware recommender systems: A systematic review", Information 10, Multidisciplinary Digital Publishing Institute, Vol. 42.
  16. Plutchik, Robert, (2001) "The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice", American scientist, Vol. 89, No. 4, pp344-350.
  17. Noroozi, Fatemeh, Kaminska, Dorota, Corneanu, Ciprian, Sapinski, Tomasz, Escalera, Sergio & Anbarjafari , Gholamreza, (2018) "Survey on emotional body gesture recognition", IEEE transactions on affective computing, IEEE.
  18. Qian, Yongfeng, Zhang, Yin, Ma, Xiao, Yu, Han & Peng, Limei, (2019) "EARS: Emotion-aware recommender system based on hybrid information fusion", Vol. 46, pp141-146.
  19. Narducci, Fedelucio, De Gemmis, Marco & Lops, Pasquale, (2015) "A general architecture for an emotion-aware content-based recommender system", In Proceedings of the 3rd Workshop on Emotions and Personality in Personalized Systems , pp3-6.
  20. Alhijawi, & Kilani, Yousef, (2020) "The recommender system: A survey. International Journal of Advanced Intelligence Paradigms ", Inderscience Publishers, Vol. 15, pp229-251.
  21. Mizgajski, Jan & Morzy, Mikolaj, (2019) ''Affective recommender systems in online news industry: how emotions influence reading choices", User Modeling and User-Adapted Interaction, Vol. 29, No. 2, pp345-379.
  22. Schroff, Florian, Kalenichenko, Dmitry & Philbin, James, (2015) "Facenet: A unified embedding for face recognition and clustering", In Proceedings of the IEEE conference on computer vision and pattern recognition, pp815-823.
  23. Alimuin, Ryann, Dadios, Elmer, Dayao, Jonathan & Arenas, Shearyl, (2020) "Deep hypersphere embedding for real-time face recognition", Telkomnika, Vol. 18.
  24. Lin, Tsung-Yi, Maire, Michael, Belongie, Serge, Hays, James, Perona, Pietro, Ramanan, Deva, Dollár, Piotr & Zitnick, C Lawrence, (2014) "Microsoft coco: Common objects in context", In European conference on computer vision, Springer, pp740-755.
  25. Kim, Dae-Hwan, (2019) "Evaluation of COCO Validation 2017 Dataset with YOLOv3", Evaluation 6,pp10356-10360.
  26. Klare, Brendan F, Klein, Ben, Taborsky, Emma, Blanton, Austin, Cheney, Jordan, Allen, Kristen, Grother, Patrick, Mah, Alan & Jain Anil K, (2015) "Pushing the frontiers of unconstrained face detection and recognition: Iarpa janus benchmark a", In Proceedings of the IEEE conference on computer vision and pattern recognition, pp1931-1939.
  27. Nada, Hajime, Sindagi, Vishwanath A., Zhang, He & Patel, Vishal M., (2018) "Pushing the limits of unconstrained face detection: a challenge dataset and baseline results", In 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS), pp1-10.
  28. Özdil, Ahmet & Özbilen, Metin Mete, (2014) "A survey on comparison of face recognition algorithms", In 2014 IEEE 8th International Conference on Application of Information and Communication Technologies (AICT), IEEE, pp1-3.
  29. Wu, Yue & Ji, Qiang (2019) " Facial landmark detection: A literature survey", International Journal of Computer Vision 127, Springer, pp115-142.
  30. De Silva, Liyanage C, Miyasato, Tsutomu & Nakatsu, Ryohei, (1997) "Facial emotion recognition using multi-modal information", In Proceedings of ICICS 1997 International Conference on Information, Communications and Signal Processing. Theme: Trends in Information Systems Engineering and Wireless Multimedia Communications, IEEE, Vol. 1, pp397-401.
  31. Zhang, Jianhua, Yin, Zhong , Chen, Peng & Nichele, Stefano, (2020) "Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review", Information Fusion 59, Elsevier,pp103-126.
  32. Maas, Andrew L., Daly, Raymond E., Pham, Peter T., Huang, Dan, Ng, Andrew Y. & Potts, Christopher, (2011) "Learning Word Vectors for Sentiment Analysis", In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA., Association for Computational Linguistics, pp142-150.
  33. Ye, Zhe, Li, Fang & Baldwin, Timothy, (2018) "Encoding sentiment information into word vectors for sentiment analysis", In Proceedings of the 27th International Conference on Computational Linguistics, pp997-1007.
  34. Rezaeinia, Seyed Mahdi, Rahmani, Rouhollah , Ghodsi, Ali & Veisi, Hadi, (2019) "Sentiment analysis based on improved pre-trained word embeddings", Expert Systems with Applications 117, Elsevier, pp139-147.
  35. Ekman, Paul, (1999) "Basic emotions", Handbook of cognition and emotion, Vol. 98, No. 45-60, pp16.
  36. Siedlecka, Ewa & Denson, Thomas F, (2019) "Experimental methods for inducing basic emotions: A qualitative review", Emotion Review 11, SAGE Publications Sage UK, London, England, pp87-97.
  37. Ekman, Paul, Friesen, Wallace V. & Ellsworth, Phoebe, (2013) "Emotion in the human face: Guidelines for research and an integration of findings", Elsevier, Vol. 11.
  38. Matsumoto, David & Hwang, Hyi Sung C, (2019) "Culture, emotion, and expression", Cross-Cultural Psychology: Contemporary Themes and Perspectives, Wiley Online Library,pp501-515.
  39. Tayib, Saifulazmi & Jamaludin, Zulikha, (2016) "An algorithm to define emotions based on facial gestures as automated input in survey instrument", Advanced Science Letters, Vol. 22, No. 10, pp2889-2893.
  40. Li, Shan & Deng, Weihong, (2020) "Deep facial expression recognition: A survey", IEEE Transactions on Affective Computing, IEEE.
  41. Van't Wout, Mascha, Kahn, René S, Sanfey, Alan G. & Aleman, André, (2006) "Affective state and decision-making in the ultimatum game", Experimental brain research, Vol. 169, No. 4, pp564-568.
  42. Heliman, Renata M, (2018) "A new look at the ultimatum game: Relational and individual differences underlying the division of gains and losses", Nova Science Publishers.
  43. Toda, Masanao (1980) "Emotion and decision making", Acta Psychologica, Vol. 45, No. 1-3, pp133- 155.
  44. Kratzwald, Bernhard, Ilić, Suzana, Kraus, Mathias , Feuerriegel, Stefan & Prendinger, Helmut,(2018) "Deep learning for affective computing: Text-based emotion recognition in decision support", Decision Support Systems , Elsevier, Vol. 115, pp24-35.
  45. Sanfey, Alan G., (2007) "Social decision-making: insights from game theory and neuroscience", Science, Vol. 318 No. 5850, pp598-602.
  46. Gu, Ruolei, Liu, Jie & Cui, Fang, (2019) "Pain and social decision-making: New insights from the social framing effect", Brain Science Advances 5, SAGE Publications Sage UK, London, England, pp221-238.
  47. Blanchette, Isabelle & Richards, Anne, (2010) "The influence of affect on higher level cognition: A review of research on interpretation, judgement, decision making and reasoning", Cognition & Emotion, Vol. 24, No. 4, pp561-595.
  48. Evans, Jonathan St BT, (2019) "Hypothetical thinking: Dual processes in reasoning and judgement", Psychology Press.
  49. Wright, William F. & Bower, Gordon H., (1992) "Mood effects on subjective probability assessment", Organizational behavior and human decision processes, Vol. 52, No. 2, pp276-291.
  50. Diener, Ed, Oishi, Shigehiro & Tay, Louis, (2018) "Advances in subjective well-being research", Nature Human Behaviour 2, Nature Publishing Group, pp253.
  51. Harper, F Maxwell & Konstan, Joseph A., (2016) "The movielens datasets: History and context", ACM Transactions on Interactive Intelligent Systems (TiiS), Vol. 5, No. 4, pp19.
  52. TMDb, (2018) "Tmdb about", Published online at www.themoviedb.org, Accessed: 2018-05-11 17:29:37.
  53. Wikipedia, (2018) "Imdb", Published online at en.wikipedia.org, Accessed: 2018-05-11 17:01:41.

Related papers

Using Affective Features from Media Content Metadata for Better Movie Recommendations
William G. Kennedy

Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, 2020

This paper investigates the causality in the decision making of movie recommendations through the users' affective profiles. We advocate a method of assigning emotional tags to a movie by the auto-detection of the affective features in the movie's overview. We apply a text-based Emotion Detection and Recognition model, which trained by tweets short messages and transfers the learned model to detect movie overviews' implicit affective features. We vectorize the affective movie tags to represent the mood embeddings of the movie. We obtain the user's emotional features by taking the average of all the movies' affective vectors the user has watched. We apply five-distance metrics to rank the Top-N movie recommendations against the user's emotion profile. We found Cosine Similarity distance metrics performed better than other distance metrics measures. We conclude that by replacing the top-N recommendations generated by the Recommender with the reranked recommendations list made by the Cosine Similarity distance metrics, the user will effectively get affective aware top-N recommendations while making the Recommender feels like an Emotion Aware Recommender.

View PDFchevron_right
Making Use of Affective Features from Media Content Metadata for Better Movie Recommendation Making
William G. Kennedy

2020

Our goal in this paper aims to investigate the causality in the decision making of movie recommendations from a Recommender perspective through the behavior of users' affective moods. We illustrate a method of assigning emotional tags to a movie by auto-detection of the affective attributes in the movie overview. We apply a text-based Emotion Detection and Recognition model, which trained by the short text of tweets, and then transfer the model learning to detect the implicit affective features of a movie from the movie overview. We vectorize the affective movie tags through embedding to represent the mood of the movie. Whereas we vectorize the user's emotional features by averaging all the watched movie's vectors, and when incorporated the average ratings from the user rated for all watched movies, we obtain the weighted vector. We apply the distance metrics of these vectors to enhance the movie recommendation making of a Recommender. We demonstrate our work through an ...

View PDFchevron_right
Improving Web Movie Recommender System Based on Emotions
Rebwar Bakhtyar

International Journal of Advanced Computer Science and Applications, 2015

Recommender Systems (RSs) are garnering a significant importance with the advent of e-commerce and ebusiness on the web. This paper focused on the Movie Recommender System (MRS) based on human emotions. The problem is the MRS need to capture exactly the customer's profile and features of movies, therefore movie is a complex domain and emotions is a human interaction domain, so difficult to combining together in the new Recommender System (RS). In this paper, we prepare a new hybrid approach for improving MRS, it consists of Content Based Filtering (CBF), Collaborative Filtering (CF), emotions detection algorithm and our algorithm, that presented by matrix. The result of our system provides much better recommendations to users because it enables the users to understand the relation between their emotional states and the recommended movies.

View PDFchevron_right
The Application of Affective Measures in Text-based Emotion Aware Recommender Systems
William G. Kennedy

arXiv (Cornell University), 2023

This paper presents an innovative approach to address the problems researchers face in Emotion Aware Recommender Systems (EARS): the difficulty and cumbersome collecting voluminously good quality emotion-tagged datasets and an effective way to protect users' emotional data privacy. Without enough goodquality emotion-tagged datasets, researchers cannot conduct repeatable affective computing research in EARS that generates personalized recommendations based on users' emotional preferences. Similarly, if we fail to protect users' emotional data privacy fully, users could resist engaging with EARS services. This paper introduced a method that detects affective features in subjective passages using the Generative Pre-trained Transformer Technology, forming the basis of the Affective Index and Affective Index Indicator (AII). Eliminate the need for users to build an affective feature detection mechanism. The paper advocates for a separation of responsibility approach where users protect their emotional profile data while EARS service providers refrain from retaining or storing it. Service providers can update users' Affective Indices in memory without saving their privacy data, providing Affective Aware recommendations without compromising user privacy. This paper offers a solution to the subjectivity and variability of emotions, data privacy concerns, and evaluation metrics and benchmarks, paving the way for future EARS research.

View PDFchevron_right
Affective recommender systems in online news industry: how emotions influence reading choices
Jan Mizgajski

User Modeling and User-Adapted Interaction

Recommender systems have become ubiquitous over the last decade, providing users with personalized search results, video streams, news excerpts, and purchasing hints. Human emotions are widely regarded as important predictors of behavior and preference. They are a crucial factor in decision making, but until recently, relatively little has been known about the effectiveness of using human emotions in personalizing real-world recommender systems. In this paper we introduce the Emotion Aware Recommender System (EARS), a large scale system for recommending news items using user's self-assessed emotional reactions. Our original contribution includes the formulation of a multi-dimensional model of emotions for news item recommendations, introduction of affective item features that can be used to describe recommended items, construction of affective similarity measures, and validation of the EARS on a large corpus of real-world Web traffic. We collect over 13,000,000 page views from 2,700,000 unique users of two news sites and we gather over 160,000 emotional reactions to 85,000 news articles. We discover that incorporating pleasant emotions into collaborative filtering recommendations consistently outperforms all other algorithms. We also find that targeting recommendations by selected emotional reactions presents a promising direction for further research. As an additional contribution we share our experiences in designing and developing a real-world emotion-based recommendation engine, pointing to various challenges posed by the practical aspects of deploying emotion-based recommenders.

View PDFchevron_right

Related topics

  • Computer Science
  • Information Retrieval
  • Machine Learning
  • Classification (Machine Learning)
  • Applications of Machine Learning
  • Context-Aware Computing
  • Affective Computing
  • Context Awareness
  • Collaborative Filtering
  • Recommender System
  • Data mining and Text mining
  • Affective Commitment
  • Recomendation Systems
  • Computer Science Information Tec...
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved