Social Reference Processing with Collaborative Human-AI Systems
Citations Over Time
Abstract
In this dissertation, I introduce several human-AI systems that can understand and process social references — language that invokes connotations by overlaying parts of social and cultural contexts. I argue that developing a rich understanding of social references is a key challenge that must be overcome in order to accomplish numerous communication tasks, especially in online environments where language rapidly develops. I demonstrate the importance of understanding social references within three case studies: in finding emotionally manipulative language and distinguishing it from other aspects of content, in identifying and understanding rhetoric that is used to marginalize people-groups, and to ensure high-quality language translations for complex terms. In each of these three case studies, I introduce social reference processing systems to overcome the challenges that limit existing systems, including systems that rely on the capabilities of crowds and machines on their own. Specifically, I use the case studies to introduce three collaborative human-AI approaches: a coordination technique that I call anchor comparison, a method for developing gold standards that can be used to identify social reference experts within a generalized crowd, and an approach for supporting people with gathering adequate context surrounding social references that I call guided context building. Together, each of my approaches make it possible to strategically recruit, coordinate, and support panels of crowdsourced experts with AI assistance for accomplishing effective social reference processing.
Related Papers
- → PACWON: A parallelizing compiler for workstations on a network(1998)
- Study and Two Types of Typical Usage of DataGrid Web Server Control(2005)
- Achieving Parameter of DBSCAN Based on Datagrid(2010)
- Using DataGrid Control to Realize DataBase of Querying in VB6.0(2000)
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)