An analysis of customer perception using lexicon-based sentiment analysis of Arabic Texts framework.

Abstract

Sentiment Analysis (SA) employing Natural Language Processing (NLP) is pivotal in determining the positivity and negativity of customer feedback. Although significant research in SA is focused on English texts, there is a growing demand for SA in other widely spoken languages, such as Arabic. This is predominantly due to the global reach of social media which enables users to express opinions on products in any language and, in turn, necessitates a thorough understanding of customers' perceptions of new products based on social media conversations. However, the current research studies demonstrate inadequacies in furnishing text analysis for comprehending the perceptions of Arabic customers towards coffee and coffee products. Therefore, this study proposes a comprehensive Lexicon-based Sentiment Analysis on Arabic Texts (LSAnArTe) framework applied to social media data, to understand customer perceptions of coffee, a widely consumed product in the Arabic-speaking world. The LSAnArTe Framework incorporates the existing AraSenTi dictionary, an Arabic database of sentiment scores for Arabic words, and lemmatizes unknown words using the Qalasadi open platform. It classifies each word as positive, negative or neutral before conducting sentence-level sentiment classification. Data collected from X (formerly known as Twitter, resulted in a cleaned dataset of 10,769 tweets, is used to validate the proposed framework, which is then compared with Amazon Comprehend. The dataset was annotated manually to ensure maximum accuracy and reliability in validating the proposed LSAnArTe Framework. The results revealed that the proposed LSAnArTe Framework, with an accuracy score of 93.79 %, outperformed the Amazon Comprehend tool, which had an accuracy of 51.90 %.