Investigating the impact of demographic and device information in the recommendation of mobile applications
DOI:
https://doi.org/10.5753/jisa.2022.2379Keywords:
Mobile Applications, Recommendation System, Demographic InformationAbstract
The number of people with access to mobile devices, as well as applications to these devices (i.e., apps), has been increasing significantly. Thus, users have to choose among a large number of apps proposing to do the same functions, those that better serve them. A possible solution to this problem is the adoption of recommendation systems. Meanwhile, usually these systems consider only users' preferences to create a profile or request sensitive data (e.g., call and message logs). This work investigates the impact of using demographic and device information on app recommendation by using only easy-to-obtain data to enrich a user profile. We evaluate two approaches: a similarity-based Collaborative Filtering with a limited number of apps and a topic-based approach (i.e., LDA) with wider large-scale data. We also inspected the results under both apps and categories context. The general results reveal that the enriched data provides a better app recommendation with the addition of information about the user's region mean wage achieving up to 210% (or 12 percentage points) of improvement in terms of recall.
Downloads
References
Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. the Journal of machine Learning research, 3:993–1022. DOI: 10.5555/944919.944937 https://dl.acm.org/doi/10.5555/944919.944937
Cheng, V. C., Chen, L., Cheung, W. K., and Fok, C.-k. (2018). A heterogeneous hidden markov model for mobile app recommendation. Knowledge and Information Systems, 57(1):207–228. DOI: 10.1007/s10115-017-1124- 3. https://doi.org/10.1007/s10115-017-1124-3
Frey, R. M., Xu, R., Ammendola, C., Moling, O., Giglio, G., and Ilic, A. (2017). Mobile recommendations based on interest prediction from consumer’s installed apps–insights from a large-scale field study. Information Systems, 71:152 – 163. DOI: 10.1016/j.is.2017.08.006 https://doi.org/10.1016/j.is.2017.08.006.
GSMA (2020). The Mobile Economy - The Mobile Economy. https://www.gsma.com/mobileeconomy. Available online at [link]
IBGE (2021). Censo Demográfico | IBGE. https://www.ibge.gov.br. [Online; accessed 7. Jan. 2021]. Ipea (2008). Available online at [link]
Ipea. http://www.ipea.gov.br. [Online; accessed 25. Fev. 2021]. Available online at [link]
Liang, T., Zheng, L., Chen, L., Wan, Y., Yu, P. S., and Wu, J. (2020). Multi-view factorization machines for mobile app recommendation based on hierarchical attention. Knowledge-Based Systems, 187:104821. DOI: 10.1016/j.knosys.2019.06.029 https://doi.org/10.1016/j.knosys.2019.06.029.
Liu, B., Kong, D., Cen, L., Gong, N. Z., Jin, H., and Xiong, H. (2015). Personalized mobile app recommendation: Reconciling app functionality and user privacy preference. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, WSDM ’15, pages 315–324, New York, NY, USA. ACM. DOI: 10.1145/2684822.2685322. http://doi.acm.org/10.1145/2684822.2685322
Liu, B., Wu, Y., Gong, N. Z., Wu, J., Xiong, H., and Ester, M. (2016). Structural analysis of user choices for mobile app recommendation. ACM Trans. Knowl. Discov. Data, 11(2):17:1–17:23. DOI: 10.1145/2983533. http://doi.acm.org/10.1145/2983533
Ma, Q., Muthukrishnan, S., and Simpson, W. (2016). App2vec: Vector modeling of mobile apps and applications. In 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pages 599–606. DOI: 10.1109/ASONAM.2016.7752297. [link]
Maia, W., Silva, F., and Silva, T. (2020). Um estudo sobre a relação entre smartphones e dados demográficos. In Anais do IV Workshop de Computação Urbana, pages 302–315, Porto Alegre, RS, Brasil. SBC. DOI: 10.5753/courb.2020.12371. [link]
Matters, . (2021). Google Play Statistics and Trends 2021| 42matters. https://42matters.com [Online; accessed 7. Jan. 2021]. Available online at [link]
Medeiros, H. (2019). Faturamento com smartphones cresce 6% no Brasil e alcança R$ 58 bilhões em 2018 - Mobile Time. https://www.mobiletime.com.br. [Online; accessed 25. Fev. 2021]. Available online at [link]
Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. DOI: 10.48550/arXiv.1301.3781. [link]
Pan, W., Aharony, N., and Pentland, A. S. (2011). Composite social network for predicting mobile apps installation. In Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI’11, pages 821–827. AAAI Press. DOI: 10.5555/2900423.2900554 https://dl.acm.org/doi/10.5555/2900423.2900554
Peng, M., Zeng, G., Sun, Z., Huang, J., Wang, H., and Tian, G. (2018). Personalized app recommendation based on app permissions. World Wide Web, 21(1):89–104. DOI: 10.1007/s11280-017-0456-y. https://doi.org/10.1007/s11280-017-0456-y
Röder, M., Both, A., and Hinneburg, A. (2015). Exploring the space of topic coherence measures. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, WSDM ’15, page 399–408, New York, NY, USA. Association for Computing Machinery. DOI: 10.1145/2684822.2685324. https://doi.org/10.1145/2684822.2685324
Sarwar, B. M., Karypis, G., Konstan, J. A., Riedl, J., et al. (2001). Item-based collaborative filtering recommendation algorithms. Www, 1:285–295. DOI: 10.1145/371920.372071. https://dl.acm.org/doi/10.1145/371920.372071
Xu, X., Dutta, K., Datta, A., and Ge, C. (2018). Identifying functional aspects from user reviews for functionalitybased mobile app recommendation. Journal of the Association for Information Science and Technology, 69(2):242– 255. DOI: 10.1002/asi.23932. https://doi.org/10.1002/asi.23932.
Yin, H., Chen, L., Wang, W., Du, X., Nguyen, Q. V. H., and Zhou, X. (2017). Mobi-sage: A sparse additive generative model for mobile app recommendation. In 2017 IEEE 33rd International Conference on Data Engineering (ICDE), pages 75–78. DOI: 10.1109/ICDE.2017.43. [link]
Zhu, K., Xiao, Y., Zheng, W., Jiao, X., and Hsu, C.-H. (2021). A novel context-aware mobile application recommendation approach based on users behavior trajectories. IEEE Access, 9:1362–1375. DOI: 10.1109/ACCESS.2020.3046654. [link]
