University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Can NLP Bots Perceive the Intensity of Emotions?
Navarro Martí, Fèlix (2025) Can NLP Bots Perceive the Intensity of Emotions?
PDF
895kB |
Abstract: | This paper explores the ability of Natural Language Processing (NLP) bots, specifically ChatGPT, to recognize and respond to the intensity of sentiment in user inputs, rather than merely detecting simple emotions. A Finite State Automaton (FSA) was developed to automate interactions with the NLP bot, generating responses that follow predefined strategies based on the sentiment scores of previous replies. These sentiment scores, ranging from -1 (very negative) to +1 (very positive), were obtained using sentiment analysis tools. Statistical analysis, including t-tests and Pearson correlation, revealed that ChatGPT’s responses are significantly influenced by the emotional intensity of prior messages. While it generally maintains a positive tone, the bot demonstrates a measurable tendency to mirror the sentiment strength of user inputs, suggesting a limited but non-negligible capacity for emotional nuance in conversational contexts. |
Item Type: | Essay (Bachelor) |
Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
Subject: | 54 computer science |
Programme: | Computer Science BSc (56964) |
Link to this item: | https://purl.utwente.nl/essays/107324 |
Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Repository Staff Only: item control page