Decoding Sentiment in Online Communication: A Social Media Analysis of Fashion Companies
Year: 2024
Type: article
Abstract: Purpose: The aim of this article was to identify differences in the emotional tone of verbal messages published on the Facebook accounts of selected companies within the fashion industry, focusing on organizations with an active presence on this platform. Design/methodology/approach: The sentiment analysis was conducted using the CLARIN software suite. Over a three-month period in 2023, companies’ posts and users’ comments were collected and analyzed. Sentiments were categorized into six groups: ambiguous statements, strong and weak negative statements, strong and weak positive statements, and neutral statements. Analysis was performed at sentence, document, and aspect levels, employing both lexicon-based methods and machine learning. Findings: The results showed a preponderance of strong positive sentiment among the messages seen on the social media channels of the companies analyzed. Research limitations/implications: The study was limited to a three-month data collection period and focused exclusively on organizations within the fashion industry with an active Facebook presence, which may limit the generalizability of the findings to other industries or platforms. Originality/value: This study contributes to the understanding of how corporate communication on social media impacts its users, offering insights specifically into sentiment dynamics within the fashion industry.
Source: European Management Studies
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4407255233