Treffer: A X Platform Analysis of The Brand Torku By Means of A Text Mining Method.

Purpose - Consumers in all sectors, and especially in the food and beverage sector, make evaluations about the products and services of businesses, and these opinions have an impact on the preferences of different consumers. The main problem of the research is how businesses can transform this multidimensional and complex big data from social media into useful insights. This study aims by means of text mining to analyze the posts shared on X platform by Torku, a brand owned by Konya Şeker, a top 50 company in Turkey operating in the food industry, using the hashtag #torku. Design/methodology/approach - For this purpose, 8208 tweets shared in Turkish on X platform were accessed using the programming language Python. The BERT model was used for the sentiment analysis. Findings - As a result of sentiment analysis, 4283 of 7212 posts were positive and 2929 were negative. The word cloud is shown that the most frequently repeated three words out of all the posts to be domestic (yerli), national (milli), and nice (güzel). Discussion - An analysis of the posts involving these related words show the most frequently highlighted facts in positive reviews to be that the brand is domestic, is national, and uses halal products, while the most frequently mentioned posts for negative reviews were that the prices are high. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Business Research-Turk / Isletme Arastirmalari Dergisi is the property of Journal of Business Research / Isletme Arastirmalari Dergisi and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)