Comparative Analysis of User-Generated Video and Text Reviews of Healthcare Products Using Multimodal NLP

Garud, Ankita Dattatray (2025) Comparative Analysis of User-Generated Video and Text Reviews of Healthcare Products Using Multimodal NLP. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study compares sentiment patterns in text-based and video-based reviews of healthcare products using a multimodal NLP approach. The texts of Amazon reviews were obtained in the form of an open Kaggle dataset, and the spoken messages were taken out of a YouTube review provided by a medical professional. In the analysis VADER was used to score on the basis of lexicon, DistilRoBERTa to score on the basis of contextual sentiment, Whisper was used to transcription, and Librosa was used to extract audio-prosodic features. Sentiment scores were assessed after preprocessing of the two datasets and to determine the variation in strength and expression of emotion in the two modalities. These findings reveal that there is a high variety of consumer opinions expressed in Amazon reviews, but the degree of positivity is moderate, whereas the emotional intensity expressed in the YouTube review is consistently higher because of the use of voice cues, including pitch and vitality. Overall, the findings highlight how spoken communication conveys heightened sentiment, whereas text reviews provide more diverse, experience-based perspectives.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Basilio, Jorge UNSPECIFIED
Uncontrolled Keywords:	Multimodal NLP; VADER; RoBERTa; Healthcare Product Reviews; Emotional Expression; Cross-Modal Comparison
Subjects:	P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing R Medicine > Healthcare Industry Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 Sep 2026 10:47
Last Modified:	07 Sep 2026 10:47
URI:	https://norma.ncirl.ie/id/eprint/9859

Actions (login required)

View Item