Enhancing User Experience With Recommender Systems Beyond Prediction Accuracies. Nguyen, T. Ph.D. Thesis, University of Minnesota, Minneapolis, MN, USA, August, 2016. ![Enhancing User Experience With Recommender Systems Beyond Prediction Accuracies [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex In this dissertation, we examine to improve the user experience with recommender systems beyond prediction accuracy. We focus on the following aspects of the user experience. In chapter 3 we examine if a recommender system exposes users to less diverse contents over time. In chapter 4 we look at the relationships between user personality and user preferences for recommendation diversity, popularity, and serendipity. In chapter 5 we investigate the relations between the self-reported user satisfaction and the three recommendation properties with the inferred user recommendation consumption. In chapter 6 we look at four different rating inter- faces and evaluated how these interfaces affected the user rating experience. We find that over time a recommender system exposes users to less-diverse contents and that users rate less-diverse items. However, users who took recommendations were exposed to more diverse recommendations than those who did not. Furthermore, users with different personalities have different preferences for recommendation diversity, popularity, and serendipity (e.g. some users prefer more diverse recommendations, while others prefer similar ones). We also find that user satisfaction with recommendation popularity and serendipity measured with survey questions strongly relate to user recommendation consumption inferred with logged data. We then propose a way to get better signals about user preferences and help users rate items in the recommendation systems more consistently. That is providing exemplars to users at the time they rate the items improved the consistency of users’ ratings. Our results suggest several ways recommender system practitioners and re- searchers can enrich the user experience. For example, by integrating users’ personality into recommendation frameworks, we can help recommender systems deliver recommendations with the preferred levels of diversity, popularity, and serendipity to individual users. We can also facilitate the rating process by integrating a set of proven rating-support techniques into the systems’ interfaces.
@phdthesis{nguyen_enhancing_2016,
address = {Minneapolis, MN, USA},
title = {Enhancing {User} {Experience} {With} {Recommender} {Systems} {Beyond} {Prediction} {Accuracies}},
url = {http://hdl.handle.net/11299/182780},
abstract = {In this dissertation, we examine to improve the user experience with
recommender systems beyond prediction accuracy. We focus on the following
aspects of the user experience. In chapter 3 we examine if a recommender
system exposes users to less diverse contents over time. In chapter 4 we
look at the relationships between user personality and user preferences
for recommendation diversity, popularity, and serendipity. In chapter 5 we
investigate the relations between the self-reported user satisfaction and
the three recommendation properties with the inferred user recommendation
consumption. In chapter 6 we look at four different rating inter- faces
and evaluated how these interfaces affected the user rating experience. We
find that over time a recommender system exposes users to less-diverse
contents and that users rate less-diverse items. However, users who took
recommendations were exposed to more diverse recommendations than those
who did not. Furthermore, users with different personalities have
different preferences for recommendation diversity, popularity, and
serendipity (e.g. some users prefer more diverse recommendations, while
others prefer similar ones). We also find that user satisfaction with
recommendation popularity and serendipity measured with survey questions
strongly relate to user recommendation consumption inferred with logged
data. We then propose a way to get better signals about user preferences
and help users rate items in the recommendation systems more consistently.
That is providing exemplars to users at the time they rate the items
improved the consistency of users’ ratings. Our results suggest several
ways recommender system practitioners and re- searchers can enrich the
user experience. For example, by integrating users’ personality into
recommendation frameworks, we can help recommender systems deliver
recommendations with the preferred levels of diversity, popularity, and
serendipity to individual users. We can also facilitate the rating process
by integrating a set of proven rating-support techniques into the systems’
interfaces.},
urldate = {2016-11-01},
school = {University of Minnesota},
author = {Nguyen, Tien},
month = aug,
year = {2016},
}
Downloads: 0
{"_id":"8dqJj5bfuRAvznkBZ","bibbaseid":"nguyen-enhancinguserexperiencewithrecommendersystemsbeyondpredictionaccuracies-2016","authorIDs":[],"author_short":["Nguyen, T."],"bibdata":{"bibtype":"phdthesis","type":"phdthesis","address":"Minneapolis, MN, USA","title":"Enhancing User Experience With Recommender Systems Beyond Prediction Accuracies","url":"http://hdl.handle.net/11299/182780","abstract":"In this dissertation, we examine to improve the user experience with recommender systems beyond prediction accuracy. We focus on the following aspects of the user experience. In chapter 3 we examine if a recommender system exposes users to less diverse contents over time. In chapter 4 we look at the relationships between user personality and user preferences for recommendation diversity, popularity, and serendipity. In chapter 5 we investigate the relations between the self-reported user satisfaction and the three recommendation properties with the inferred user recommendation consumption. In chapter 6 we look at four different rating inter- faces and evaluated how these interfaces affected the user rating experience. We find that over time a recommender system exposes users to less-diverse contents and that users rate less-diverse items. However, users who took recommendations were exposed to more diverse recommendations than those who did not. Furthermore, users with different personalities have different preferences for recommendation diversity, popularity, and serendipity (e.g. some users prefer more diverse recommendations, while others prefer similar ones). We also find that user satisfaction with recommendation popularity and serendipity measured with survey questions strongly relate to user recommendation consumption inferred with logged data. We then propose a way to get better signals about user preferences and help users rate items in the recommendation systems more consistently. That is providing exemplars to users at the time they rate the items improved the consistency of users’ ratings. Our results suggest several ways recommender system practitioners and re- searchers can enrich the user experience. For example, by integrating users’ personality into recommendation frameworks, we can help recommender systems deliver recommendations with the preferred levels of diversity, popularity, and serendipity to individual users. We can also facilitate the rating process by integrating a set of proven rating-support techniques into the systems’ interfaces.","urldate":"2016-11-01","school":"University of Minnesota","author":[{"propositions":[],"lastnames":["Nguyen"],"firstnames":["Tien"],"suffixes":[]}],"month":"August","year":"2016","bibtex":"@phdthesis{nguyen_enhancing_2016,\n\taddress = {Minneapolis, MN, USA},\n\ttitle = {Enhancing {User} {Experience} {With} {Recommender} {Systems} {Beyond} {Prediction} {Accuracies}},\n\turl = {http://hdl.handle.net/11299/182780},\n\tabstract = {In this dissertation, we examine to improve the user experience with\nrecommender systems beyond prediction accuracy. We focus on the following\naspects of the user experience. In chapter 3 we examine if a recommender\nsystem exposes users to less diverse contents over time. In chapter 4 we\nlook at the relationships between user personality and user preferences\nfor recommendation diversity, popularity, and serendipity. In chapter 5 we\ninvestigate the relations between the self-reported user satisfaction and\nthe three recommendation properties with the inferred user recommendation\nconsumption. In chapter 6 we look at four different rating inter- faces\nand evaluated how these interfaces affected the user rating experience. We\nfind that over time a recommender system exposes users to less-diverse\ncontents and that users rate less-diverse items. However, users who took\nrecommendations were exposed to more diverse recommendations than those\nwho did not. Furthermore, users with different personalities have\ndifferent preferences for recommendation diversity, popularity, and\nserendipity (e.g. some users prefer more diverse recommendations, while\nothers prefer similar ones). We also find that user satisfaction with\nrecommendation popularity and serendipity measured with survey questions\nstrongly relate to user recommendation consumption inferred with logged\ndata. We then propose a way to get better signals about user preferences\nand help users rate items in the recommendation systems more consistently.\nThat is providing exemplars to users at the time they rate the items\nimproved the consistency of users’ ratings. Our results suggest several\nways recommender system practitioners and re- searchers can enrich the\nuser experience. For example, by integrating users’ personality into\nrecommendation frameworks, we can help recommender systems deliver\nrecommendations with the preferred levels of diversity, popularity, and\nserendipity to individual users. We can also facilitate the rating process\nby integrating a set of proven rating-support techniques into the systems’\ninterfaces.},\n\turldate = {2016-11-01},\n\tschool = {University of Minnesota},\n\tauthor = {Nguyen, Tien},\n\tmonth = aug,\n\tyear = {2016},\n}\n\n","author_short":["Nguyen, T."],"key":"nguyen_enhancing_2016","id":"nguyen_enhancing_2016","bibbaseid":"nguyen-enhancinguserexperiencewithrecommendersystemsbeyondpredictionaccuracies-2016","role":"author","urls":{"Paper":"http://hdl.handle.net/11299/182780"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"phdthesis","biburl":"https://api.zotero.org/users/6655/collections/TJPPJ92X/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","creationDate":"2020-03-27T02:34:35.331Z","downloads":0,"keywords":[],"search_terms":["enhancing","user","experience","recommender","systems","beyond","prediction","accuracies","nguyen"],"title":"Enhancing User Experience With Recommender Systems Beyond Prediction Accuracies","year":2016,"dataSources":["5Dp4QphkvpvNA33zi","jfoasiDDpStqkkoZB","BiuuFc45aHCgJqDLY"]}