Analysis and comparison of generative AI chatbot applications

Loading...
Thumbnail Image

Supplementary material

Other Title

Authors

Ahuja, Maghav

Author ORCID Profiles (clickable)

Degree

Master of Applied Technologies (Computing)

Grantor

Unitec, Te Pūkenga – New Zealand Institute of Skills and Technology

Date

2024

Supervisors

Sharifzadeh, Hamid

Type

Masters Thesis

Ngā Upoko Tukutuku (Māori subject headings)

Keyword

ChatGPT
evaluation
chatbots
project management technologies
text data mining
intelligent personal assistants (computer software)
natural language generation (computer science)

ANZSRC Field of Research Code (2020)

Citation

Ahuja, M. (2024). Analysis and comparison of generative AI chatbot applications (Unpublished document submitted in partial fulfilment of the requirements for the degree of Master of Applied Technologies (Computing)). Unitec, Te Pūkenga - New Zealand Institute of Skills and Technology https://hdl.handle.net/10652/6493

Abstract

RESEARCH QUESTIONS RQ1: How can AI chatbots responses be analysed using text mining techniques? RQ2: How can AI-enhanced project management tool responses be analysed using text mining techniques? RQ3: How well are these AI-enhanced project management tools integrated with their AI feature? ABSTRACT This research proposes the analysis to systematically evaluate and compare ChatGPT API applications operating within two categories: AI chatbots and project management tools. The primary aim is to analyse the generative AI chatbots to assess these applications based on domain-specific criteria, aligning with the intended functionalities of their AI feature using various text mining techniques. The evaluation methodology involves tailored strategies for each category. Text mining techniques are applied for chatbots to assess coherence, relevance, and completeness within the generated text, providing a quantitative basis for comparison. Concurrently, the project management tools undergo text mining analysis with some AI integration feature comparison, including the data utilisation analysis, which they offer to evaluate documentation, summarisation, sentiment analysis, and other types of scores. The chatbots include CopyAI, HuggingFace chatbot, ChatSonic, YouChat and Rytr.me, and project management tools include ClickUp, Notion and Jira as they support the “Write with AI” feature. This research seeks to evaluate GPT-powered applications by leveraging text-mining techniques. It intends to provide insights into the strengths and weaknesses of these applications, aiding users in making informed decisions based on specific requirements within each category.

Publisher

Link to ePress publication

DOI

Copyright holder

Author

Copyright notice

All rights reserved

Copyright license

Available online at