Next-App Prediction by Fusing Semantic Information With Sequential Behavior
Next-App Prediction by Fusing Semantic Information With Sequential Behavior
复制标题
DOI：
10.1109/access.2018.2883377
复制
发表时间：
2018
期刊：
影响因子：
3.9
通讯作者：
Changjian Fang;Youquan Wang;Dejun Mu;Zhiang Wu
中科院分区：
文献类型：
--
作者：
Changjian Fang;Youquan Wang;Dejun Mu;Zhiang Wu
下一个应用程序预测是预测用户将选择在智能手机上使用的下一个应用程序的任务。它有助于建立各种智能个性化服务，例如快速启动UI应用程序，智能用户与手机交互等。由于应用程序名称仅提供有限的语义信息，无法充分利用应用程序之间的内在联系。同时，要使用的下一个应用主要由用户最近使用的应用的序列确定。为了解决这些具有挑战性的问题，本文首先丰富的应用程序的语义信息，从应用程序商店中提取每个应用程序的描述性文本，从而提出了一个主题模型，将应用程序以及用户偏好转化为潜在向量。然后，可以基于特征向量的相似性构造一组最近邻，并将其用于训练预测模型。此外，我们的预测方案是建立在时间序列数据，并使用链增强朴素贝叶斯模型建模。使用真实的智能手机应用程序日志数据的实验结果表明，与几种基线下一个应用程序预测方法相比，我们的方法实现了更高的召回率和DCG值。
Next-app prediction is the task of predicting the next app that a user will choose to use on the smartphone. It helps to establish a variety of intelligent personalized services, such as fast-launch UI app, intelligent user-phone interactions, and so on. Since app names only provide limited semantic information, the intrinsic relation among apps cannot be fully exploited. Meanwhile, next-app to be used is largely determined by a sequence of apps that a user used recently. To address these challenging problems, this paper first enriches the semantic information of apps by extracting descriptive text of each app from the app store and thus proposes a topic model to transform apps as well as user preferences into latent vectors. Then, a set of nearest neighbors can be constructed based on the similarity of latent vectors and it is employed for training the prediction model. Furthermore, our prediction scheme is built on the temporal sequential data and is modeled by using the chain-augmented Naive Bayes model. Experimental results with a real smartphone application log data have demonstrated that our method achieves higher recall and DCG values compared with several baseline next-app prediction methods.