Abstract
Keeping fit has always been the focus of public attention, so the emergence of fitness apps has been highly sought after. However, after the outbreak, updates to fitness apps often disappoint their users. Therefore, it is eager for developers to learn about the real requirements and opinions to their apps. To investigate users’ requirements, we take data mining on user reviews, and apply sentiment analysis to obtain users’ evaluations and suggestions on the attributes and functions of fitness apps. The users of fitness apps have a high follow-up, and usually have been using these apps for a long time, leaning to treat them as daily applications, and can clearly perceive the experience brought by apps during the process. Therefore, users are very serious when evaluating the apps, and the reviews include user requirements, ideas for improvements, positive and negative sentiments about specific features, and descriptions of experiences with these features. Based on the characteristics of the reviews, we use the P-N deep analysis method to perform sentiment analysis on user reviews. For each review, we extract the active and negative evaluations of the corresponding features separately to avoid errors in evaluating features of apps only based on the star rating of the reviews. And when extracting sentiment words in sentiment analysis, verbs are added as features words and adverbs are added as emotion words because users of fitness apps use more adverbs than that of other apps to express their feelings and many nouns can be expressed by verbs in Chinese.
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
References
Wu, R., Wang, Q.: Research on development status, problems and countermeasures of sports fitness app. J. Shandong Inst. Phys. Educ. 04, 22–26 (2015)
Zhang, X., Zhao, Y., Yang, Y.: Research on the experience of college students using fitness apps under the new media environment. China School Phys. Educ. (High. Educ.) 05, 7–12 (2017)
Wang, X., Zhou, Y., Cao, G.: “Xingxiu”—research on mobile phone APP for college students. Mod. Bus. Ind. 03, 70–71 (2019)
Jiang, M., Song, D., Liao, L., et al.: A Bayesian recommender model for user rating and review profiling. J. Tsinghua Univ. (Engl. Version), 20, 634–643 (2015)
Guzman, E., Maalej, W.: How do users like this feature? A fine-grained sentiment analysis of app reviews. In: 2014 IEEE 22nd International Requirements Engineering Conference, RE 2014 – Proceedings, pp. 153–162 (2014). https://doi.org/10.1109/re.2014.6912257
Li, H., Qian, L., Zhou, P.: Sentiment analysis and mining for product review texts. Inf. Sci. 01, 53–57 (2017)
Ma, S., Xu, X.: Research on user online evaluation based on comment sentiment analysis—taking Douban movie as an example. Libr. Inf. Serv. 10, 95–102 (2016)
Li, H., Zhang, H.: A method for sentiment analysis of book reviews based on word vector and CNN. J. Test Measur. Technol. 02, 165–171 (2019)
Tsou, B.K.Y., Yuen, R.W.M., Kwong, O.Y., et al.: Polarity classification of celebrity coverage in the Chinese press, 105–111 (2005)
Taboada, M., Brooke, J., Tofiloski, M., et al.: Lexicon-based methods for sentiment analysis. Comput. Linguist. 37, 267–307 (2011)
Wang, X., Shi, L.: Commodity comprehensive scoring model based on emotion quantification of web reviews. J. Hangzhou Dianzi Univ.: Soc. Sci. Ed. 03, 8–15 (2016)
Chen, Y., Huang, Z., Shi, X.: An SNN-based semantic role labeling model with its network parameters optimized using an improved PSO algorithm. Neural Process. Lett. 44, 245–263 (2016). https://doi.org/10.1007/s11063-015-9449-y
Turney, P.D.: Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. In: Proceedings of Annual Meeting of the Association for Computational Linguistics, pp. 417–424 (2002)
Guo, S.: Improving the algorithm of information gain feature selection in text classification. Comput. Appl. Softw. 30, 139–142 (2013)
Meng, J., Duan, X., Yang, L.: Tendency analysis of cross-domain product reviews based on feature transformation. Comput. Eng. 10, 167–171 (2013)
Li, T., Wang, B., Mao, E., et al.: Analysis of sentiment orientation of Weibo based on Skip-gram model. J. Comput. Appl. Softw. 07, 114–117 (2016)
Zhang, D., Yang, P., Xu, Y.: Research of Chinese comments sentiment classification based on Word2vec and SVMperf. Comput. Sci. 43, 418–421 (2016)
Huang, R., Zhang, W.: Study on sentiment analysis of internet commodities review based on word2vec. Comput. Sci. 43, 387–389 (2016)
Gan, L., Wan, C., Liu, D., et al.: Chinese entity relation extraction based on syntactic and semantic features. J. Comput. Res. Dev. 53, 284–302 (2016)
Tang, Z., Long, Y.: Research on personalized demand acquisition method based on Kano model. Soft Sci. 02, 131–135 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wen, P., Chen, M. (2020). A New Analysis Method for User Reviews of Mobile Fitness Apps. In: Kurosu, M. (eds) Human-Computer Interaction. Human Values and Quality of Life. HCII 2020. Lecture Notes in Computer Science(), vol 12183. Springer, Cham. https://doi.org/10.1007/978-3-030-49065-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-49065-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-49064-5
Online ISBN: 978-3-030-49065-2
eBook Packages: Computer ScienceComputer Science (R0)