Understanding Mobile User Intent Using Attentive Sequence-to-Sequence RNNs

Smartphones have become an indispensable part of our lives. Understanding user behaviors based on smartphone usage data is therefore critical to many applications. In this paper, we propose to address a novel task called Intention2Text which attempts to capture user intents based on smartphone usage log. The goal of Intention2Text is to learn a deep learning model taking mobile context logs as input and generate sentences as output for describing mobile user intentions. So far, we have developed an attentive sequence-to-sequence recurrent neural network for the Intention2Text task as a fundamental model. Also, various model encoding/decoding strategies are introduced and considered. The experiments based on a real community question dataset are conducted to verify the effectiveness of the proposed framework.

[1]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[2]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[3]  Xing Xie,et al.  Mining interesting locations and travel sequences from GPS trajectories , 2009, WWW '09.

[4]  Jun Rekimoto,et al.  LifeTag: WiFi-Based Continuous Location Logging for Life Pattern Analysis , 2007, LoCA.

[5]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[7]  Tae-Seong Kim,et al.  A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer , 2010, IEEE Transactions on Information Technology in Biomedicine.

[8]  Y.-K. Lee,et al.  Human Activity Recognition via an Accelerometer-Enabled-Smartphone Using Kernel Discriminant Analysis , 2010, 2010 5th International Conference on Future Information Technology.

[9]  Huiru Zheng,et al.  Activity Monitoring Using a Smart Phone's Accelerometer with Hierarchical Classification , 2010, 2010 Sixth International Conference on Intelligent Environments.

[10]  Arbee L. P. Chen,et al.  A Framework for Enabling User Preference Profiling through Wi-Fi Logs , 2016, IEEE Trans. Knowl. Data Eng..

[11]  Jun Yang,et al.  Toward physical activity diary: motion recognition using simple acceleration features with mobile phones , 2009, IMCE '09.

[12]  Xing Xie,et al.  Towards mobile intelligence: Learning from GPS history data for collaborative recommendation , 2012, Artif. Intell..

[13]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[14]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[15]  Lin Sun,et al.  Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations , 2010, UIC.

[16]  A. Stewart Fotheringham,et al.  Analysis of human mobility patterns from GPS trajectories and contextual information , 2016, Int. J. Geogr. Inf. Sci..