Date of Completion

2022

Document Type

Honors College Thesis

Department

Computer Science

Thesis Type

College of Arts and Science Honors, Honors College

First Advisor

Joe Near

Second Advisor

Nick Cheney

Keywords

intent analysis, context analysis, natural language processing, NLP, AI, machine learning

Abstract

Intent analysis is the problem in computer science and natural language processing of taking a user utterance and predicting the user’s intent. Conversational agents that analyze user intent from spoken or typed utterances are used in general use cases, such as the iPhone’s Siri or the Android Google Assistant, and specific topic areas, such as a digital assistant on a bank’s website. These conversational agents frequently struggle to accurately predict intent from ambiguous utterances. Without a user’s usage context, it is impossible for the computer to accurately predict the correct user intent in some scenarios. This research project aims to fill this gap by developing a context analyzer for intent analysis, in order to enrich existing intent analysis solutions with contextual information.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Share

COinS