Application of Logistic Regression Analysis of Smartphone Speech Interaction Usage in China: A Questionnaire-Based Study of 622 Adults
Speech interaction as one of the contact-free input techniques has been applied in mobile devices (e.g. smartphone) for many years, which means that a considerable number of users were exposed to speech interaction. In China, speech interaction, while undoubtedly natural, has also entered users’ life for more than 5 years but it is still perceived as “not that good”. Curiosities are stimulated that what barriers are that prevent speech from becoming one of the mainstream interaction modality in China, yet there is no research on the user experience of mobile speech interaction. An online questionnaire was used to measure participants’ speech interaction use of smartphone. Simple Logistic Regression Model and Ordinal Logistic Regression Model were used as the primary method of data analysis. This study concluded that speech interaction is an interactive modality for the future and need to give full play to the advantages of speech interaction by reducing interface exclusivity, offering services to users actively in combination with situational awareness and guiding users in a variety of modalities.
KeywordsSpeech interaction Questionnaire-based Logistic regression analysis
- 1.Munteanu, C., Cowan, B., Nakamura, K., Irani, P., Oviatt, S., Aylett, M., et al.: Designing speech, acoustic and multimodal interactions. In: The 2017 CHI Conference Extended Abstracts, pp. 601–608. ACM Press, New York (2017)Google Scholar
- 3.Lokosang, L.: Statistical analysis of determinants of household food insecurity in post conflict Southern Sudan, University of KwaZulu-Natal (Master’s thesis) (2009)Google Scholar
- 6.Harrell, F., Margolis, P., Gove, S., Mason, K., Mulholland, E., Lehmann, D., et al.: Tutorial in biostatistics: development of a clinical prediction model for an ordinal outcome: the World Health Organization ARI Multicenter Study of clinical signs and etiological agents of pneumonia, sepsis, and meningitis in young infants. Stat. Med. 17, 909–944 (1998)Google Scholar
- 10.Gemeroff, M.: Using the proportional odds model for health-related outcomes: why, when, and how with various SAS® procedures. In: The Proceedings of the Thirtieth Annual SAS Users Group International Conference, Paper # 205-30. SAS Institute Inc., Philadelphia (2005)Google Scholar