2016/11/21 by Reza Rawassizadeh, Chelsea Dobbins, Rawassizadeh, Reza +7
Computer Science · Engineering · Social Sciences · #Computation and Language (cs.CL) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Green IT and Sustainability #Human Mobility and Location-Based Analysis #Human-Computer Interaction (cs.HC) #Information Retrieval (cs.IR) #Innovative Human-Technology Interaction #Recommender Systems and Techniques
paper · pdf · doi:10.48550/arxiv.1611.07139
openalex publication_date 2016/11/21 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28
Currently, personal assistant systems, run on smartphones and use natural\nlanguage interfaces. However, these systems rely mostly on the web for finding\ninformation. Mobile and wearable devices can collect an enormous amount of\ncontextual personal data such as sleep and physical activities. These\ninformation objects and their applications are known as quantified-self, mobile\nhealth or personal informatics, and they can be used to provide a deeper\ninsight into our behavior. To our knowledge, existing personal assistant\nsystems do not support all types of quantified-self queries. In response to\nthis, we have undertaken a user study to analyze a set of "textual\nquestions/queries" that users have used to search their quantified-self or\nmobile health data. Through analyzing these questions, we have constructed a\nlight-weight natural language based query interface, including a text parser\nalgorithm and a user interface, to process the users' queries that have been\nused for searching quantified-self information. This query interface has been\ndesigned to operate on small devices, i.e. smartwatches, as well as augmenting\nthe personal assistant systems by allowing them to process end users' natural\nlanguage queries about their quantified-self data.\n