Abstract
In recent years, mobile applications (apps) on smartphones have shown explosive growth. Massive and diversified apps greatly affect user experience. As a result, user mobile app behavior prediction has become increasingly important. Existed algorithms based on deep learning mainly conduct sequence modeling on the app usage historical records, which are insufficient in capturing the similarity between users and apps, and ignore the semantic associations in app usage. Although some works have tried to model from the perspective of graph structure recently, the two types of modeling methods have not been combined, and whether they are complementary has not been explored. Therefore, we propose an SGFNN model based on sequence combined graph modeling, which is already publicly available as the GitHub repository https://github.com/ZAY113/SGFNN. Sequence Block, BipGraph Block, and HyperGraph Block are used to capture the user mobile app behavior short-term pattern, the similarity between users and apps, and the semantic relations of hyperedge “user-time-location-app”, respectively. Two real-world datasets are selected in our experiments. When the app sequence length is 4, the prediction accuracy of Top1, Top5, and Top10 reaches 36.08%, 68.39%, 79.02% and 51.55%, 87.57%, 95.62%, respectively. The experimental results show that the two modeling methods can be combined to improve prediction accuracy, and the information extracted from them is complementary.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
van den Berg, R., Kipf, T.N., Welling, M.: Graph convolutional matrix completion. arXiv preprint arXiv:1706.02263 (2017)
Ceci, L.: App stores - statistics & facts (2022)
Chen, Q., et al.: DualSIN: dual sequential interaction network for human intentional mobility prediction. In: Proceedings of the 28th International Conference on Advances in Geographic Information Systems, pp. 283–292 (2020)
Chen, X., Wang, Y., He, J., Pan, S., Li, Y., Zhang, P.: CAP: context-aware app usage prediction with heterogeneous graph embedding. Proc. ACM Interactive Mobile Wearable Ubiquit. Technol. 3(1), 1–25 (2019)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Association for Computational Linguistics, Doha, Qatar (2014)
De Nadai, M., Cardoso, A., Lima, A., Lepri, B., Oliver, N.: Strategies and limitations in app usage and human mobility. Sci. Rep. 9(1), 10935 (2019)
Do, T.M.T., Gatica-Perez, D.: Where and what: using smartphones to predict next locations and applications in daily life. Pervasive Mob. Comput. 12, 79–91 (2014)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, K., Zhang, C., Ma, X., Chen, G.: Predicting mobile application usage using contextual information. In: Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pp. 1059–1065 (2012)
Jiang, R., et al.: Will you go where you search? A deep learning framework for estimating user search-and-go behavior. Neurocomputing 472, 338–348 (2022)
Jiang, Y., Du, X., Jin, T.: Using combined network information to predict mobile application usage. Physica A 515, 430–439 (2019)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Lee, Y., Cho, S., Choi, J.: App usage prediction for dual display device via two-phase sequence modeling. Pervasive Mob. Comput. 58, 101025 (2019)
Li, T., et al.: Smartphone app usage analysis: datasets, methods, and applications. IEEE Commun. Surv. Tutorials 2, 937–966 (2022)
Li, Y., Fan, Z., Yin, D., Jiang, R., Deng, J., Song, X.: HMGCL: heterogeneous multigraph contrastive learning for LBSN friend recommendation. World Wide Web 26, 1625–1648 (2022)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579–2605 (2008)
Natarajan, N., Shin, D., Dhillon, I.S.: Which app will you use next? Collaborative filtering with interactional context. In: Proceedings of the 7th ACM Conference on Recommender Systems, pp. 201–208 (2013)
Parate, A., Böhmer, M., Chu, D., Ganesan, D., Marlin, B.M.: Practical prediction and prefetch for faster access to applications on mobile phones. In: Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 275–284 (2013)
Shin, C., Hong, J.H., Dey, A.K.: Understanding and prediction of mobile application usage for smart phones. In: Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pp. 173–182 (2012)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Wang, H., Li, Y., Du, M., Li, Z., Jin, D.: App2Vec: context-aware application usage prediction. ACM Trans. Knowl. Discov. Data (TKDD) 15(6), 1–21 (2021)
Wang, H., et al.: Modeling spatio-temporal app usage for a large user population. Proc. ACM Interactive Mobile Wearable Ubiquit. Technol. 3(1), 1–23 (2019)
Xia, T., et al.: DeepApp: predicting personalized smartphone app usage via context-aware multi-task learning. ACM Trans. Intell. Syst. Technol. (TIST) 11(6), 1–12 (2020)
Xu, S., Li, W., Zhang, X., Gao, S., Zhan, T., Lu, S.: Predicting and recommending the next smartphone apps based on recurrent neural network. CCF Trans. Pervasive Comput. Interaction 2(4), 314–328 (2020)
Xu, Y., et al.: Preference, context and communities: a multi-faceted approach to predicting smartphone app usage patterns. In: Proceedings of the 2013 International Symposium on Wearable Computers, pp. 69–76 (2013)
Yang, D., Qu, B., Yang, J., Cudre-Mauroux, P.: Revisiting user mobility and social relationships in LBSNs: a hypergraph embedding approach. In: The World Wide Web Conference, pp. 2147–2157 (2019)
Yu, D., Li, Y., Xu, F., Zhang, P., Kostakos, V.: Smartphone app usage prediction using points of interest. Proc. ACM Interactive Mobile Wearable Ubiquit. Technol. 1(4), 1–21 (2018)
Yu, Y., Xia, T., Wang, H., Feng, J., Li, Y.: Semantic-aware spatio-temporal app usage representation via graph convolutional network. Proc. ACM Interactive Mobile Wearable Ubiquit. Technol. 4(3), 1–24 (2020)
Zhao, S., et al.: AppUsage2Vec: modeling smartphone app usage for prediction. In: 2019 IEEE 35th International Conference on Data Engineering (ICDE), pp. 1322–1333. IEEE (2019)
Zhao, X., Qiao, Y., Si, Z., Yang, J., Lindgren, A.: Prediction of user app usage behavior from geo-spatial data. In: Proceedings of the Third International ACM SIGMOD Workshop on Managing and Mining Enriched Geo-Spatial Data, pp. 1–6 (2016)
Zhou, Y., Li, S., Liu, Y.: Graph-based method for app usage prediction with attributed heterogeneous network embedding. Future Internet 12(3), 58 (2020)
Zou, X., Zhang, W., Li, S., Pan, G.: Prophet: what app you wish to use next. In: Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing Adjunct Publication, pp. 167–170 (2013)
Acknowledgment
This work was supported by Huawei Technologies Co., Ltd., National Key Research and Development Project of China (2021YFB1714400), and Guangdong Provincial Key Laboratory (2020B121201001).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
In this study, we introduce an innovative technique for predicting the next app by leveraging user mobile app behavior data. To implement this, our work utilizes two datasets - China Telecom app usage dataset, which is publicly available, and a distinct proprietary dataset acquired through collaboration with Huawei. We have strictly followed ethical guidelines to protect the privacy and integrity of individuals and entities involved in this study.
Data Sources and Anonymization
The China Telecom app usage dataset has been widely used in previous research and is considered ethically acceptable. Meanwhile, the Huawei app usage dataset is provided by our collaborative partner, Huawei. It is important to mention that the visualizations in our case study section do not raise any ethical concerns. This is because the users, locations, and apps of both datasets have been anonymized to protect user privacy.
Ethical Compliance
Our study follows ethical principles to handle sensitive data responsibly. We obtained permission for datasets, ensured anonymity and privacy, and complied with data protection regulations. We did not disclose any data to unauthorized parties and put in place security measures to prevent misuse or unauthorized access.
In summary, our research methodology prioritizes ethical considerations, utilizing anonymized data and safeguards to protect sensitive information. Our commitment affirms ethical guidelines adherence with reliable results, ultimately contributing to progress in predicting mobile app user behavior based on usage data, while ensuring the accuracy and dependability of our findings.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Y., Jiang, R., Liu, H., Yin, D., Song, X. (2023). Sequence-Graph Fusion Neural Network for User Mobile App Behavior Prediction. In: De Francisci Morales, G., Perlich, C., Ruchansky, N., Kourtellis, N., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14174. Springer, Cham. https://doi.org/10.1007/978-3-031-43427-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-43427-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43426-6
Online ISBN: 978-3-031-43427-3
eBook Packages: Computer ScienceComputer Science (R0)
