Artificial intelligence (AI) in mobile applications has grown in popularity, changing the way people engage with technology. AI improves functionality, personalization, and efficiency across a wide range of mobile applications. One specific group of apps powered by AI is period-tracking applications, which is the focus of this master thesis. These apps utilize AI for features such as cycle predictions, fertility windows, symptom predictions, health insights, and chatbots. The aim of this project was to evaluate the performance of these advanced features, leading to the research question: “How do users perceive and experience the AI features in period-tracking applications?” To address this question, an observational mixed-method approach was employed. The research began with a survey, shared via social media platforms from February 19th, 2024, to April 2nd, 2024. The questionnaire included 20 open-ended and multiple-choice questions centered on AI features. By the end of the survey period, 61 responses were collected and analyzed. During the survey period, four participants were chosen for follow-up interviews, but three users’ responses were used in the analysis. The survey results underwent statistical tests to explore the relationship between monthly app usage, duration of app use, and satisfaction with cycle predictions. Later, interview results analyzed by using thematic analysis were integrated to the walkthrough method while assessing the functionality, interface, and user experience of AI features. The mixed-method study offered comprehensive insights into users' practices and experiences with AI features in period-tracking apps, revealing the need for future work to enhance the performance of these AI features for better user satisfaction.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:uu-532945 |
Date | January 2024 |
Creators | Mirzaliyeva, Maysara |
Publisher | Uppsala universitet, Institutionen för informatik och media |
Source Sets | DiVA Archive at Upsalla University |
Language | English |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0091 seconds