Miriam Greis, Tilman Dingler, A. Schmidt, C. Schmandt
{"title":"利用用户做出的预测来帮助理解个人行为模式","authors":"Miriam Greis, Tilman Dingler, A. Schmidt, C. Schmandt","doi":"10.1145/3098279.3122147","DOIUrl":null,"url":null,"abstract":"People use more and more applications and devices that quantify daily behavior such as the step count or phone usage. Purely presenting the collected data does not necessarily support users in understanding their behavior. In recent research, concepts such as learning by reflection are proposed to foster behavior change based on personal data. In this paper, we introduce user-made predictions to help users understand personal behavior patterns. Therefore, we developed an Android application that tracks users' screen-on and unlock patterns on their phone. The application asks users to predict their daily behavior based on their former usage data. In a user study with 12 participants, we showed the feasibility of leveraging user-made predictions in a quantified self approach. By trying to improve their predictions over the course of the study, participants automatically discovered new insights into personal behavior patterns.","PeriodicalId":120153,"journal":{"name":"Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Leveraging user-made predictions to help understand personal behavior patterns\",\"authors\":\"Miriam Greis, Tilman Dingler, A. Schmidt, C. Schmandt\",\"doi\":\"10.1145/3098279.3122147\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"People use more and more applications and devices that quantify daily behavior such as the step count or phone usage. Purely presenting the collected data does not necessarily support users in understanding their behavior. In recent research, concepts such as learning by reflection are proposed to foster behavior change based on personal data. In this paper, we introduce user-made predictions to help users understand personal behavior patterns. Therefore, we developed an Android application that tracks users' screen-on and unlock patterns on their phone. The application asks users to predict their daily behavior based on their former usage data. In a user study with 12 participants, we showed the feasibility of leveraging user-made predictions in a quantified self approach. By trying to improve their predictions over the course of the study, participants automatically discovered new insights into personal behavior patterns.\",\"PeriodicalId\":120153,\"journal\":{\"name\":\"Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3098279.3122147\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3098279.3122147","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Leveraging user-made predictions to help understand personal behavior patterns
People use more and more applications and devices that quantify daily behavior such as the step count or phone usage. Purely presenting the collected data does not necessarily support users in understanding their behavior. In recent research, concepts such as learning by reflection are proposed to foster behavior change based on personal data. In this paper, we introduce user-made predictions to help users understand personal behavior patterns. Therefore, we developed an Android application that tracks users' screen-on and unlock patterns on their phone. The application asks users to predict their daily behavior based on their former usage data. In a user study with 12 participants, we showed the feasibility of leveraging user-made predictions in a quantified self approach. By trying to improve their predictions over the course of the study, participants automatically discovered new insights into personal behavior patterns.