Understanding the Impact of Individual Users’ Rating Characteristics on the Predictive Accuracy of Recommender Systems. Cheng, X., Zhang, J., & Yan, L. (. INFORMS J. Comput., 32(2):303–320, April, 2020. Publisher: INFORMS![Understanding the Impact of Individual Users’ Rating Characteristics on the Predictive Accuracy of Recommender Systems [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 1 download In this study, we investigate how individual users? rating characteristics affect the user-level performance of recommendation algorithms. We measure users? rating characteristics from three perspectives: rating value, rating structure, and neighborhood network embeddedness. We study how these three categories of measures influence the predictive accuracy of popular recommendation algorithms for each user. Our experiments use five real-world data sets with varying characteristics. For each individual user, we estimate the predictive accuracy of three recommendation algorithms. We then apply regression-based models to uncover the relationships between rating characteristics and recommendation performance at the individual user level. Our experimental results show consistent and significant effects of several rating measures on recommendation accuracy. Understanding how rating characteristics affect the recommendation performance at the individual user level has practical implications for the design of recommender systems.
@article{cheng_understanding_2020,
title = {Understanding the {Impact} of {Individual} {Users}’ {Rating} {Characteristics} on the {Predictive} {Accuracy} of {Recommender} {Systems}},
volume = {32},
issn = {1091-9856},
url = {https://doi.org/10.1287/ijoc.2018.0882},
doi = {10.1287/ijoc.2018.0882},
abstract = {In this study, we investigate how individual users? rating characteristics
affect the user-level performance of recommendation algorithms. We measure
users? rating characteristics from three perspectives: rating value,
rating structure, and neighborhood network embeddedness. We study how
these three categories of measures influence the predictive accuracy of
popular recommendation algorithms for each user. Our experiments use five
real-world data sets with varying characteristics. For each individual
user, we estimate the predictive accuracy of three recommendation
algorithms. We then apply regression-based models to uncover the
relationships between rating characteristics and recommendation
performance at the individual user level. Our experimental results show
consistent and significant effects of several rating measures on
recommendation accuracy. Understanding how rating characteristics affect
the recommendation performance at the individual user level has practical
implications for the design of recommender systems.},
number = {2},
journal = {INFORMS J. Comput.},
author = {Cheng, Xiaoye and Zhang, Jingjing and Yan, Lu (lucy)},
month = apr,
year = {2020},
note = {Publisher: INFORMS},
pages = {303--320},
}
Downloads: 1
{"_id":"FRZcdqNLFv67JPdqS","bibbaseid":"cheng-zhang-yan-understandingtheimpactofindividualusersratingcharacteristicsonthepredictiveaccuracyofrecommendersystems-2020","authorIDs":[],"author_short":["Cheng, X.","Zhang, J.","Yan, L. (."],"bibdata":{"bibtype":"article","type":"article","title":"Understanding the Impact of Individual Users’ Rating Characteristics on the Predictive Accuracy of Recommender Systems","volume":"32","issn":"1091-9856","url":"https://doi.org/10.1287/ijoc.2018.0882","doi":"10.1287/ijoc.2018.0882","abstract":"In this study, we investigate how individual users? rating characteristics affect the user-level performance of recommendation algorithms. We measure users? rating characteristics from three perspectives: rating value, rating structure, and neighborhood network embeddedness. We study how these three categories of measures influence the predictive accuracy of popular recommendation algorithms for each user. Our experiments use five real-world data sets with varying characteristics. For each individual user, we estimate the predictive accuracy of three recommendation algorithms. We then apply regression-based models to uncover the relationships between rating characteristics and recommendation performance at the individual user level. Our experimental results show consistent and significant effects of several rating measures on recommendation accuracy. Understanding how rating characteristics affect the recommendation performance at the individual user level has practical implications for the design of recommender systems.","number":"2","journal":"INFORMS J. Comput.","author":[{"propositions":[],"lastnames":["Cheng"],"firstnames":["Xiaoye"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Jingjing"],"suffixes":[]},{"propositions":[],"lastnames":["Yan"],"firstnames":["Lu","(lucy)"],"suffixes":[]}],"month":"April","year":"2020","note":"Publisher: INFORMS","pages":"303–320","bibtex":"@article{cheng_understanding_2020,\n\ttitle = {Understanding the {Impact} of {Individual} {Users}’ {Rating} {Characteristics} on the {Predictive} {Accuracy} of {Recommender} {Systems}},\n\tvolume = {32},\n\tissn = {1091-9856},\n\turl = {https://doi.org/10.1287/ijoc.2018.0882},\n\tdoi = {10.1287/ijoc.2018.0882},\n\tabstract = {In this study, we investigate how individual users? rating characteristics\naffect the user-level performance of recommendation algorithms. We measure\nusers? rating characteristics from three perspectives: rating value,\nrating structure, and neighborhood network embeddedness. We study how\nthese three categories of measures influence the predictive accuracy of\npopular recommendation algorithms for each user. Our experiments use five\nreal-world data sets with varying characteristics. For each individual\nuser, we estimate the predictive accuracy of three recommendation\nalgorithms. We then apply regression-based models to uncover the\nrelationships between rating characteristics and recommendation\nperformance at the individual user level. Our experimental results show\nconsistent and significant effects of several rating measures on\nrecommendation accuracy. Understanding how rating characteristics affect\nthe recommendation performance at the individual user level has practical\nimplications for the design of recommender systems.},\n\tnumber = {2},\n\tjournal = {INFORMS J. Comput.},\n\tauthor = {Cheng, Xiaoye and Zhang, Jingjing and Yan, Lu (lucy)},\n\tmonth = apr,\n\tyear = {2020},\n\tnote = {Publisher: INFORMS},\n\tpages = {303--320},\n}\n\n","author_short":["Cheng, X.","Zhang, J.","Yan, L. (."],"key":"cheng_understanding_2020","id":"cheng_understanding_2020","bibbaseid":"cheng-zhang-yan-understandingtheimpactofindividualusersratingcharacteristicsonthepredictiveaccuracyofrecommendersystems-2020","role":"author","urls":{"Paper":"https://doi.org/10.1287/ijoc.2018.0882"},"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"article","biburl":"https://api.zotero.org/users/6655/collections/TJPPJ92X/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","creationDate":"2020-10-23T07:37:04.719Z","downloads":1,"keywords":[],"search_terms":["understanding","impact","individual","users","rating","characteristics","predictive","accuracy","recommender","systems","cheng","zhang","yan"],"title":"Understanding the Impact of Individual Users’ Rating Characteristics on the Predictive Accuracy of Recommender Systems","year":2020,"dataSources":["5Dp4QphkvpvNA33zi","jfoasiDDpStqkkoZB","BiuuFc45aHCgJqDLY"]}