Analyzing the Effectiveness of Chatbots vs. Webforms for Suspicious Activity Reporting

Date

2024-01-03

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

7152

Ending Page

Alternative Title

Abstract

Crime prevention requires the public to provide information about suspicious or illicit activity to authorities, typically through either a webform or a telephone hotline. Yet, these technologies have myriad problems in design, accessibility, and usability – all of which decrease reports and hinder prevention efforts. To address these limitations, we developed a prototype chatbot to improve reporting. In a lab experiment, participants watched a video containing a suspicious activity scenario and were randomly assigned to report it through either a standard webform or our prototype chatbot. We then compared multiple dimensions including report quality, user perceptions of the technology, and user experience/system utilization including eye-tracking data. Results indicate that the chatbot may encourage increased report accuracy in some cases. Differences in the sentiment of the report were also identified. Findings provide guidance for both the development of SAR technologies and the decision of when to deploy a chatbot vs a webform in a more general case.

Description

Keywords

Illicit Activity and Criminal Justice, chatbot, crime, interaction, trust, usability

Citation

Extent

10 pages

Format

Geographic Location

Time Period

Related To

Proceedings of the 57th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.