University of Illinois at Urbana-Champaign
Comparing how conversational agents’ modalities and apparent genders affects in correcting health misinformation
Abstract
dc:descriptionThis study compared the effectiveness of using conversational agents to debunk sunscreen usage related health misinformation. A 2 (agent gender: female, male) × 2 (agent modality: text-based, voice based) between-subjects experimental design was used with 775 U.S. participants. Implementing key theoretical perspectives from human-computer interaction literature and cognitive load theory, this study examines both agent gender and agent modality in how effectively interaction with conversational agents can correct misperceptions resulting from exposure to health misinformation. Results show that text-based agents are more successful in reducing misperceptions about sunscreen usage misinformation than voice-based agents. Agent gender did not significantly impact misperception after intervention, nor have an interaction with agent modality. These findings extend human-computer interaction, cognitive load theory and the transient information effect to the context of health misinformation correction. Practical implications of the study show that conversational agents hold great potential for public health communication, but it emphasizes the importance of managing cognitive load in voice-based interactions to enhance their effectiveness.
Degree
thesis:*- Name thesis:degree_name
- M.S.
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Advertising
- Grantor
- University of Illinois at Urbana-Champaign
- Year dc:date
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rahman, Nisa
- Contributors dc:contributor
-
- Su, Leona Y
- Sar, Sela
- Vargas, Patrick
Subjects
dc:subject × 5Rights
dc:rights- Statement dc:rights
-
- Copyright 2024 Nisa Rahman
- Language dc:language
- en, eng
Identifiers
dc:identifier.*- Handle dc:identifier
- https://hdl.handle.net/2142/127499