Comparing NLP Tools and AI Generators in the Context of Achieving Optimal Textual Analysis in an Educational Setting

Main Article Content

Katerina Florou

Abstract

In recent years, automated tools have played a pivotal role in reshaping research within the humanities and social sciences. The term "Digital Humanities," coined in 2001, according to Ref. [1], introduces a groundbreaking approach that empowers researchers to delve into texts without physical contact. This approach highlights the potential benefits of micro and macro analysis when integrated with humanities studies. In this study, students explore the dual facets of digitalization accessible through the Internet: NLP Tools and AI generators. Implemented in a semester-course at the University of Athens under the umbrella of "Digital Humanities," the academic program spans various foreign language departments. Within this framework, students employ NLP online tools to conduct comprehensive textual analyses, including tasks such as extracting term frequencies within corpora and assessing texts based on linguistic attributes, density, readability, and other relevant parameters. Specifically, the integration of ChatGPT is recommended for literary texts in Italian, Greek, or English, offering students a rich exposure to online tools that seamlessly blend applied linguistics with literary analysis. The core of this proposal revolves around the conceptualization of an instructional activity where students employ sophisticated NLP online tools like Voyant Tools. Subsequently, they replicate the same analytical process using ChatGPT [2] for the identical text, leading to a comparative evaluation of the outcomes. In the realm of big data, a Natural Language Processing (NLP) tool proves advantageous due to its specialized design for processing extensive corpora. However, limitations arise in the free edition of ChatGPT, as it doesn't support lengthy texts. Consequently, the applicability of this investigation and the ensuing comparison of these two methodologies are confined to instances where the literary text under consideration is a poem or constitutes a small passage from a novel.

Article Details

How to Cite
Florou, K. (2024). Comparing NLP Tools and AI Generators in the Context of Achieving Optimal Textual Analysis in an Educational Setting. International Journal on Recent and Innovation Trends in Computing and Communication, 11(9), 5407–5412. Retrieved from https://ijritcc.org/index.php/ijritcc/article/view/10655
Section
Articles