@phdthesis{lansman_using_2025,
	type = {Ph.{D}. {Dissertation}},
	title = {Using emotion diversification based on movie reviews to improve the user experience of movie recommender systems},
	url = {https://www.proquest.com/docview/3196617694},
	abstract = {Movies are made with the intention of evoking an emotional response. In recent years, researchers have hypothesized that the emotional response evoked by a movie can be leveraged to augment recommender system algorithms. In this work, we demonstrate that emotion diversification improves the user experience of a movie recommender system. We augmented the 10M MovieLens dataset with values of the eight dimensions of Plutchik’s wheel of emotions by leveraging an emotion analysis method that extracts these eight dimensions from movie reviews on IMDB to form an ’emotional signature’. Based on the finding of Mokryn et al. (October 2020) that showed that a film’s emotional signature reflects the emotions the film elicits in viewers, we used each movie’s emotional signature to diversify the output of our recommender algorithm. We tested this novel emotion diversification method against an existing latent diversification method and a baseline version without diversification in an online user experiment with a custom-built movie recommender system. We also tested two different types of visualization, a graph view against a baseline of a list view, as the graph view would increase user understandability regarding the reason behind the recommended items provided. The results of this study show that the emotion diversification method significantly improves the user experience of the movie recommender system, surpassing both the baseline system and the latent diversification method in terms of perceived taste coverage and system satisfaction without significantly reducing the perceived recommendation quality or increasing the trade-off difficulty. Going beyond the traditional rating and/or interaction data used by traditional recommender systems, our work demonstrates the user experience benefits of extracting emotional data from rich, qualitative user feedback and using it to give users a more emotionally diverse set of recommendations.},
	language = {English},
	author = {Lansman, Lior},
	year = {2025},
	note = {ISBN: 9798311930970
Pages: 83},
	keywords = {0489:Information Technology, Decision making, Emotions, Information technology, Motion pictures, Recommender systems, User behavior},
}

{"_id":"kbiD7kHX4dShrzBch","bibbaseid":"lansman-usingemotiondiversificationbasedonmoviereviewstoimprovetheuserexperienceofmovierecommendersystems-2025","author_short":["Lansman, L."],"bibdata":{"bibtype":"phdthesis","type":"Ph.D. Dissertation","title":"Using emotion diversification based on movie reviews to improve the user experience of movie recommender systems","url":"https://www.proquest.com/docview/3196617694","abstract":"Movies are made with the intention of evoking an emotional response. In recent years, researchers have hypothesized that the emotional response evoked by a movie can be leveraged to augment recommender system algorithms. In this work, we demonstrate that emotion diversification improves the user experience of a movie recommender system. We augmented the 10M MovieLens dataset with values of the eight dimensions of Plutchik’s wheel of emotions by leveraging an emotion analysis method that extracts these eight dimensions from movie reviews on IMDB to form an ’emotional signature’. Based on the finding of Mokryn et al. (October 2020) that showed that a film’s emotional signature reflects the emotions the film elicits in viewers, we used each movie’s emotional signature to diversify the output of our recommender algorithm. We tested this novel emotion diversification method against an existing latent diversification method and a baseline version without diversification in an online user experiment with a custom-built movie recommender system. We also tested two different types of visualization, a graph view against a baseline of a list view, as the graph view would increase user understandability regarding the reason behind the recommended items provided. The results of this study show that the emotion diversification method significantly improves the user experience of the movie recommender system, surpassing both the baseline system and the latent diversification method in terms of perceived taste coverage and system satisfaction without significantly reducing the perceived recommendation quality or increasing the trade-off difficulty. Going beyond the traditional rating and/or interaction data used by traditional recommender systems, our work demonstrates the user experience benefits of extracting emotional data from rich, qualitative user feedback and using it to give users a more emotionally diverse set of recommendations.","language":"English","author":[{"propositions":[],"lastnames":["Lansman"],"firstnames":["Lior"],"suffixes":[]}],"year":"2025","note":"ISBN: 9798311930970 Pages: 83","keywords":"0489:Information Technology, Decision making, Emotions, Information technology, Motion pictures, Recommender systems, User behavior","bibtex":"@phdthesis{lansman_using_2025,\n\ttype = {Ph.{D}. {Dissertation}},\n\ttitle = {Using emotion diversification based on movie reviews to improve the user experience of movie recommender systems},\n\turl = {https://www.proquest.com/docview/3196617694},\n\tabstract = {Movies are made with the intention of evoking an emotional response. In recent years, researchers have hypothesized that the emotional response evoked by a movie can be leveraged to augment recommender system algorithms. In this work, we demonstrate that emotion diversification improves the user experience of a movie recommender system. We augmented the 10M MovieLens dataset with values of the eight dimensions of Plutchik’s wheel of emotions by leveraging an emotion analysis method that extracts these eight dimensions from movie reviews on IMDB to form an ’emotional signature’. Based on the finding of Mokryn et al. (October 2020) that showed that a film’s emotional signature reflects the emotions the film elicits in viewers, we used each movie’s emotional signature to diversify the output of our recommender algorithm. We tested this novel emotion diversification method against an existing latent diversification method and a baseline version without diversification in an online user experiment with a custom-built movie recommender system. We also tested two different types of visualization, a graph view against a baseline of a list view, as the graph view would increase user understandability regarding the reason behind the recommended items provided. The results of this study show that the emotion diversification method significantly improves the user experience of the movie recommender system, surpassing both the baseline system and the latent diversification method in terms of perceived taste coverage and system satisfaction without significantly reducing the perceived recommendation quality or increasing the trade-off difficulty. Going beyond the traditional rating and/or interaction data used by traditional recommender systems, our work demonstrates the user experience benefits of extracting emotional data from rich, qualitative user feedback and using it to give users a more emotionally diverse set of recommendations.},\n\tlanguage = {English},\n\tauthor = {Lansman, Lior},\n\tyear = {2025},\n\tnote = {ISBN: 9798311930970\nPages: 83},\n\tkeywords = {0489:Information Technology, Decision making, Emotions, Information technology, Motion pictures, Recommender systems, User behavior},\n}\n\n","author_short":["Lansman, L."],"key":"lansman_using_2025","id":"lansman_using_2025","bibbaseid":"lansman-usingemotiondiversificationbasedonmoviereviewstoimprovetheuserexperienceofmovierecommendersystems-2025","role":"author","urls":{"Paper":"https://www.proquest.com/docview/3196617694"},"keyword":["0489:Information Technology","Decision making","Emotions","Information technology","Motion pictures","Recommender systems","User behavior"],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"phdthesis","biburl":"https://api.zotero.org/users/6655/collections/3TB3KT36/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","dataSources":["7KNAjxiv2tsagmbgY"],"keywords":["0489:information technology","decision making","emotions","information technology","motion pictures","recommender systems","user behavior"],"search_terms":["using","emotion","diversification","based","movie","reviews","improve","user","experience","movie","recommender","systems","lansman"],"title":"Using emotion diversification based on movie reviews to improve the user experience of movie recommender systems","year":2025,"downloads":1}