Bidirectional sensing of user preferences and application changes for dynamic mobile app recommendations


Recent years have witnessed the rapid adoption of mobile devices and significant growth in the use of mobile apps. However, the large number of mobile apps makes it difficult for users to determine which ones are of interest. Current app recommendation methods focus on the similarities between user interest and mobile app functionality at a single moment, but they do not consider how these change over time and do not address the underlying mutual effect of such changes. This paper describes a bidirectional sensing method for user interest and app changes that enables precise mobile app recommendations. The proposed method applies continuous bidirectional sensing to both user interest and the functional changes to apps and obtains the evolution trajectory of both. Then, a personal interest evolution network is used to learn the relationship between the two trajectories. Finally, user interest in an app is predicted, and the top-N strategy is used to recommend suitable apps. Experiments on real data sets show that our method can accurately sense user interests and functional changes to apps, and that recommendations based on the personal interest evolution network correspond to actual recommendation scenarios.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10


  1. 1.

    Abka AF (2016) Evaluating the use of word embeddings for part-of-speech tagging in Bahasa Indonesia. In: 2016 International conference on computer, control, informatics and its applications (IC3INA), pp 209–214. IEEE

  2. 2.

    Aggarwal CC, Zhai CX (2012) Mining text data. In: A survey of opinion mining and sentiment analysis, pp 415–463.

  3. 3.

    Arifin AZ, Abdullah MZ, Rosyadi AW et al (2018) Sentence extraction based on sentence distribution and part of speech tagging for multi-document summarization. TELKOMNIKA Telecommun Comput Elect Control 16(2):843–851

    Google Scholar 

  4. 4.

    Balusu MRB, Merghani T, Eisenstein J (2018) Stylistic variation in social media part-of-speech tagging. arXiv preprint arXiv:1804.07331 

  5. 5.

    Brill ED (1995) Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging. Comput Linguist 21(4):543–565

    Google Scholar 

  6. 6.

    Califf ME, Mooney RJ (1998) Relational learning of pattern-match rules for information extraction. University of Texas, Austin

  7. 7.

    Chapelle O, Zhang Y (2009) A dynamic Bayesian network click model for web search ranking. In: Proceedings of the 18th international conference world wide web, ACM

  8. 8.

    Chen N, Lin J, Hoi SC, Xiao X, Zhang B (2014) Ar-miner: mining informative reviews for developers from mobile app marketplace. In: Proceedings of the 36th international conference on software engineering, pp 767–778. ACM

  9. 9.

    Chen B, Jin H, Yang Z et al (2019) An approach for transgender population information extraction and summarization from clinical trial text. BMC Med Inform Decis Making 19(2):159–170

    Google Scholar 

  10. 10.

    Cheng H, Koc L, Harmsen J et al (2016) Wide & deep learning for recommender systems. In: Conference on recommender systems, pp 7–10

  11. 11.

    de Amo S, Bueno MLP, Alves G, da Silva NFF (2013) Mininguser contextual preferences. Inf Data Manag 4:37C46

    Google Scholar 

  12. 12.

    Deng AL, Zhu YY, Shi BL (2013) A collaborative filtering recommendation algorithm based on item rating prediction. J Softw 14(9):1621–1628

    MATH  Google Scholar 

  13. 13.

    Fu B, Lin J, Li L, Faloutsos C, Hong J, Sadeh N (2013) Why people hate your app: making sense of user feedback in a mobile app store. In: Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1276–1284. ACM

  14. 14.

    Hawalah A, Fasli M (2015) Dynamic user profiles for web personalisation. Expert Syst Appl 42(5):2547–2569

    Article  Google Scholar 

  15. 15.

    Lee DD, Seung HS (2014) Algorithms for non-negative matrix factorization. In: Advances in neural information processing systems, pp 556–562

  16. 16.

    Leeuwenberg A, Moens M (2019) A survey on temporal reasoning for temporal information extraction from text. J Artif Intel Res 66:341–380

    MathSciNet  Article  Google Scholar 

  17. 17.

    Liu L, Shang J, Xu FF et al (2017) Empower sequence labeling with task-aware neural language model. arXiv: Computation and Language 

  18. 18.

    Nadeau D, Sekine S (2007) A survey of named entity recognition and classification. Lingvisticae Invest 30(1):3–26

    Article  Google Scholar 

  19. 19.

    Pratiwi PS, Tjondronegoro DW, Xu Y et al (2018) Automated e-Coaching system architecture framework for promoting physical activity. In: International conference on intelligent autonomous systems

  20. 20.

    Rahmati A, Zhong L (2012) Studying smartphone usage: lessons from a four-month field study. IEEE Trans Mobile Comput 12(7):1417–1427

    Article  Google Scholar 

  21. 21.

    Rahmati A, Tossell C, Shepard C et al (2012) Exploring iPhone usage: the influence of socioeconomic differences on smartphone adoption, usage and usability. In: International conference on human-computer interaction with mobile devices & services

  22. 22.

    Rahmati A, Zhong L (2013) Studying smartphone usage: lessons from a four-month field study. IEEE Trans Mobile Comput 12(7):1417

    Article  Google Scholar 

  23. 23.

    Ravindranath L, Padhye J, Agarwal S, Mahajan R, Obermiller I, Shayandeh S (2012) Appinsight: mobile app performance monitoring in the wild. In: Presented as part of the 10th {USENIX} symposium on operating systems design and implementation ({OSDI} 12), pp 107–120

  24. 24.

    Salonen V, Karjaluoto H (2016) Web personalization: the state of the art and future avenues for research and practice. Telematics Inform 33(4):1088–1104

    Article  Google Scholar 

  25. 25.

    Shi K, Ali K (2012) Getjar mobile application recommendations with very sparse datasets. In: Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 204–212. ACM

  26. 26.

    Sun QS, Zeng SG, Liu Y, Heng PA, Xia DS (2017) A new method of feature fusion and its application in image recognition. Pattern Recogn 38(12):2437–2448

    Article  Google Scholar 

  27. 27.

    Wang L-C, Meng X-W, Zhang Y-J (2012) Context aware recommendation system. J Software 23(1):1–20

    Article  Google Scholar 

  28. 28.

    Wang J, Zeng C, He C, Hong L, Zhou L, Wong RK, Tian J et al (2012) Context-aware role mining for mobile service recommendation. In: Proceedings of the 27th annual ACM symposium on applied computing, pp 173–178. ACM

  29. 29.

    Wang L, Meng X, Zhang Y, Shi Y (2015) New approaches to mood-based hybrid collaborative filtering. In: Proceedings of the workshop on context-aware movie recommendation, pp 28–33. ACM

  30. 30.

    Wang YX, Qiao XQ, Li XF, Meng LM (2016) Research on context-awareness mobile sns service selection mechanism. Jisuanji Xuebao (Chinese Journal of Computers) 33(11):2126–2135

    Google Scholar 

  31. 31.

    Wang S, Zhao Y, Huang L et al (2017) QoS prediction for service recommendations in mobile edge computing. J Parallel Distrib Comput 2017:134–144

    Google Scholar 

  32. 32.

    Wang X, Zhang Y, Ren X et al (2019) Cross-type biomedical named entity recognition with deep multi-task learning. Bioinformatics 35(10):1745–1752

    Article  Google Scholar 

  33. 33.

    Xu J, He H, Sun X et al (2018) Cross-domain and semisupervised named entity recognition in Chinese social media: a unified model. IEEE Trans Audio Speech Lang Process 26(11):2142–2152

    Article  Google Scholar 

  34. 34.

    Yang YC (2010) Web user behavioral profiling for user identification. Decis Support Syst 49(3):261–271

    Article  Google Scholar 

  35. 35.

    Yu Q et al (2012) Decision tree learning from incomplete QoS to bootstrap service recommendation. In: Proceeding of IEEE international conference on web services, pp 194–201. IEEE

  36. 36.

    Yu Z, Zhou X, Zhang D, Chin CY, Wang X, Men J (2016) Supporting context-aware media recommendations for smart phones. IEEE Pervasive Comput 5(3):68–75

    Google Scholar 

  37. 37.

    Zhang Z, Liu Y, Xu G, Chen H (2016) A weighted adaptation method on learning user preference profile. Knowl Based Syst 112:114–126

    Article  Google Scholar 

  38. 38.

    Zhao L, Hu NJ, Zhang SZ (2012) Algorithm design for personalization recommendation systems. J Comput Res Develop 39(8):986–991

    Google Scholar 

  39. 39.

    Zhou G, Zhu X, Song C, Fan Y, Zhu H, Ma X, Yan Y, Jin J, Li H, Gai K (2018) Deep interest network for click-through rate prediction. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1059–1068. ACM

Download references


Research in this study was partially supported by the National Key Research and Development Program of China (No 2018YFB1004804) and the National Science Foundation of China (61772155, 61802089, 61832004, 61832014).

Author information



Corresponding author

Correspondence to Zhongjie Wang.

Ethics declarations

Conflict of interest

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work. There is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled, “Bidirectional Sensing of User Preferences and Application Changes for Dynamic Mobile App Recommendations”.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Tu, Z., Duan, B., Wang, Z. et al. Bidirectional sensing of user preferences and application changes for dynamic mobile app recommendations. Neural Comput & Applic (2021).

Download citation


  • Mobile app recommendation
  • Personal interest evolution network
  • User preference