PREDICTING CUSTOMER SATISFACTION THROUGH ONLINE REVIEW ANALYTICS: A CASE STUDY IN A POINT-OF-SALES COMPANY IN INDONESIA

• Main Author: Zakaria, Anas
• Format: Theses
• Language: Indonesia
• Subjects: Manajemen umum
• Online Access: https://digilib.itb.ac.id/gdl/view/70640
• Institution: Institut Teknologi Bandung

The recent digital environment development drives the generation of a vast amount of user-generated content. User-generated content, such as user reviews, posts, tags, ratings, and opinions on the internet, can be used as a business indicator if collected and appropriately analyzed, for example, by predicting customer satisfaction through implementing big data analytics. In analyzing the user-generated content data to predict customer satisfaction, the author implements the Sentiment Analysis method. Five-fold cross-validation was performed to train the classification model. The training was performed with a combination of vectorization methods: term frequency-inverse document frequency (tf-idf) and bag-of-words; n-gram types: unigram, bigram, trigram, and combination of unigram, bigram, and trigram; and model algorithms: linear support vector classification (LinearSVC) and multinomial naïve bayes (MultinomialNB). The result was then evaluated using classification performance metrics such as precision, recall, F1 measure, and AUC score. The result shows that the tf-idf vectorizer performs similarly to the bag-of-words method. A similar result was also observed for machine learning algorithm selection. Both the Support Vector Machine and Naïve Bayes produce the same result performance. The result shows that Naïve Bayes and Support Vector Machine are decent sentiment analysis classifiers. Low-level n-grams (such as unigrams and bigrams) tended to have better precision, recall, F1 measure, and AUC score than high-order n-grams (such as trigrams). The best results were achieved by combining unigrams, bigrams, and trigrams, resulting in an average performance score of 0.94 for all measurements. From the result and analysis, the author finds that predicting customer satisfaction using text and sentiment analysis methods on user-generated content is possible. The model’s performance in this experiment is decent, with high precision, recall, F1, and AUC score.