TY - JOUR
T1 - Version-Aware rating prediction for mobile app recommendation
AU - Yao, Yuan
AU - Zhao, Wayne Xin
AU - Wang, Yaojing
AU - Tong, Hanghang
AU - Xu, Feng
AU - Lu, Jian
N1 - Funding Information:
This work was supported by the National Key Research and Development Program of China (2016YFB1000802), National 863 Program of China (2015AA01A203), National Natural Science Foundation of China (61672274, 61690204), the Collaborative Innovation Center of Novel Software Technology and Industrialization, and Program A for Outstanding PhD candidate of Nanjing University. X. Zhao was partially supported by the National Natural Science Foundation of China under grant 61502502 and the Beijing Natural Science Foundation under grant 4162032. H. Tong was partially supported by DTRA under grant HDTRA1-16-0017, the Army Research Office under contract W911NF-16-1-0168, the National Institutes of Health under grant R01LM011986, the Region II University Transportation Center under project 49997-33 25, and a Baidu gift.
Publisher Copyright:
© 2017 ACM.
PY - 2017/6
Y1 - 2017/6
N2 - With the great popularity of mobile devices, the amount of mobile apps has grown at a more dramatic rate than ever expected. A technical challenge is how to recommend suitable apps to mobile users. In this work, we identify and focus on a unique characteristic that exists in mobile app recommendation-That is, an app usually corresponds to multiple release versions. Based on this characteristic, we propose a fine-grain version-Aware app recommendation problem. Instead of directly learning the users' preferences over the apps, we aim to infer the ratings of users on a specific version of an app. However, the user-version rating matrix will be sparser than the corresponding user-App rating matrix, making existing recommendation methods less effective. In view of this, our approach has made two major extensions. First, we leverage the review text that is associated with each rating record; more importantly, we consider two types of versionbased correlations. The first type is to capture the temporal correlations between multiple versions within the same app, and the second type of correlation is to capture the aggregation correlations between similar apps. Experimental results on a large dataset demonstrate the superiority of our approach over several competitive methods.
AB - With the great popularity of mobile devices, the amount of mobile apps has grown at a more dramatic rate than ever expected. A technical challenge is how to recommend suitable apps to mobile users. In this work, we identify and focus on a unique characteristic that exists in mobile app recommendation-That is, an app usually corresponds to multiple release versions. Based on this characteristic, we propose a fine-grain version-Aware app recommendation problem. Instead of directly learning the users' preferences over the apps, we aim to infer the ratings of users on a specific version of an app. However, the user-version rating matrix will be sparser than the corresponding user-App rating matrix, making existing recommendation methods less effective. In view of this, our approach has made two major extensions. First, we leverage the review text that is associated with each rating record; more importantly, we consider two types of versionbased correlations. The first type is to capture the temporal correlations between multiple versions within the same app, and the second type of correlation is to capture the aggregation correlations between similar apps. Experimental results on a large dataset demonstrate the superiority of our approach over several competitive methods.
KW - App rating prediction
KW - Recommender systems
KW - Version correlation
UR - http://www.scopus.com/inward/record.url?scp=85021806966&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021806966&partnerID=8YFLogxK
U2 - 10.1145/3015458
DO - 10.1145/3015458
M3 - Article
AN - SCOPUS:85021806966
SN - 1046-8188
VL - 35
JO - ACM Transactions on Information Systems
JF - ACM Transactions on Information Systems
IS - 4
M1 - 3015458
ER -