A Knowledge Graph Based Approach to Social Science Surveys

Recent success of knowledge graphs has spurred interest in applying them open science, such as on intelligent survey systems for scientists. However, efforts to understand the quality candidate questions provided by these methods have been limited. Indeed, existing do not consider type on-the-fly content planning that is possible face-to-face surveys and hence guarantee selection subsequent based response previous a survey. To address this limitation, we propose dynamic informative solution an system graphs. illustrate our proposal, look into social science surveys, focusing ordering questionnaire component their level acceptance, along with conditional triggers further customise participants' experience. Our main findings are: (i) evaluation proposed approach shows can be beneficial terms lowering number asked per variable, thus allowing more data collected equivalent length; (ii) primary advantage it enables grouping participants according responses, so are only served appropriate follow-up questions, but responses may analysed context some initial categorisation. We believe easily applied other definitions contexts. The knowledge-graph-based work allows online questionnaires interaction informativity responsiveness, well duplicating certain advantages interview-based collection.