Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
1 results
Search Results
Item Restricted DESIGN AND EVALUATION OF A CONVERSATIONAL AGENT FOR SUPPORTING DOMESTIC VIOLENCE SURVIVORS(The University of North Carolina at Charlotte, 2024-06-19) Aldkheel, Abdulrahman; Zhou, LinaDomestic violence (DV) is widely recognized as a significant problem with detrimental impacts on the mental, physical, and socio-economic well-being of individuals, families, and the broader community. Despite various resources designated to support survivors, they may not be easily accessible or readily available. More importantly, DV survivors often hesitate to disclose their experiences to others and may even refrain from seeking assistance because of social, emotional, privacy, and cultural concerns. As providing immediate support in response to DV is crucial for the physical and psychological well-being of survivors, they need timely assistance from non-judgmental first responders. Technological advancements, particularly in automated Conversational Agent (CA), are progressing rapidly. CAs are gaining attention as a promising tool for providing counseling and support, addressing the above-mentioned challenges faced by survivors using traditional support resources. The primary objective of this dissertation research is to design, develop, and evaluate a CA-based solution that assists DV survivors in accessing services more easily, increasing their awareness, and enhancing the available support. To this end, we first identify the meta requirements and design principles of CA for survivors by interviewing DV professionals, then design and develop SafeHaven, a CA-based prototype for supporting DV survivors by following the design principles and meeting the specified meta requirements, and finally evaluate the effectiveness and perception of SafeHaven by conducting user experiments. Our findings suggest that CAs should empathize with survivors' experiences and provide them with meaningful informational, tangible, and emotional support, prioritizing their safety and maintaining transparent, private, and trustworthy communication. We evaluated SafeHaven with DV survivors, their friends and family, and DV professionals, in terms of emotional, informational, and instrumental support it provided, among other measures. In addition, we compared the CA with a traditional search engine and emerging ChatGPT. The experiment results show that SafeHaven outperformed both search engine and ChatGPT in offering emotional, informational, and instrumental support, high information quality, and user trust. This dissertation research identifies the meta-requirements and design principles for designing a CA for DV survivors. This is the first study that assesses the effectiveness of CAs in assisting individuals who experience DV and/or provide support to DV survivors, and providing tailored, context-sensitive support to them. In a broader sense, the outcomes of this research will be instrumental in guiding the future development of CA-based support systems for DV survivors. This dissertation highlights the transformative potential of CAs for DV survivors, as well as significant implications for DV organizations, support groups, and CA developers, proposing novel avenues and strategies for enhancing the anonymity and accessibility of the support for survivors.28 0