Sentimen Analisis Customer Review Produk Shopee Indonesia Menggunakan Algortima Naïve Bayes Classifier

Abstract

Gaining customer satisfaction and trust has become the main challenge in achieving success in the business world. Business people need to identify problems that arise from reviews given by customers. However, reading and classifying each review takes a long time and is considered ineffective. To overcome this, this study aims to analyze the customer sentiment of shopee products using the nave Bayes classifier algorithm. The data used in this study is a customer review of the Xiaomi Redmi Note 9 products which are sold on the Shopee Indonesia website. Customer review data is collected by applying the Web Scraping technique. The algorithm used in this study is the Naïve Bayes Classifier which is known to be popular and effective in classifying data. This study also applies the Knowledge Discovery in Text (KDT) methodology to extract information from text data. The results of the classification using the Naïve Bayes algorithm found an accuracy value of 85%. This study proves that by applying sentiment analysis techniques, business people are able to find out the opinions of customers as an evaluation material that needs to be done to optimize the products and services provided.

Comparison of Naïve Bayes Algorithm and XGBoost on Local Product Review Text Classification

“…The method proposed by the authors can also overcome other problems related to duplication of reviews or tests. This has proven to be able to overcome weaknesses regarding misclassified data (Sihombing et al, 2021). With the same method using TF-IDF and Naive Bayes, this study has a higher cause of 0.892% compared to the previous study which was only 0.85%.…”

“…Preprocessing also serves to optimize the mining process because the data is not always in good condition and structured. As done by Sihombing et al (2021) when classifying review text on Shopee using Naïve Bayes, it produces an accuracy of 85%, there is still misclassified data. This makes a reference for the author to optimize the preprocessing stages in the form of case folding, remove punctuation, stop word removal, short word removal, word normalization, stemming and tokenization so that data duplication, missing values can be resolved.…”

“…This makes a reference for the author to optimize the preprocessing stages in the form of case folding, remove punctuation, stop word removal, short word removal, word normalization, stemming and tokenization so that data duplication, missing values can be resolved. Naïve Bayes is one of the efficient and fast classification methods in classifying text (Sihombing et al, 2021), the amount of data will certainly affect the selection of the right method.…”

“…This is because, according to Nurdin et al (2020) the advantage of word2vec embedding is that it is able to process semantic relationships between words better than TF-IDF. The research that be carried out will also optimize the preprocessing process for unstructured text data to be cleaned and able to be processed by the classification algorithm so that classification errors such as in the study can be corrected (Sihombing et al, 2021). Thus, this study will try to compare the performance of the Naïve Bayes and XGBoost algorithms against online reviews in the marketplace, which will later be measured using a confusion matrix.…”

Perbandingan Algoritma Naïve Bayes, SVM Dan Xgboost Dalam Klasifikasi Teks Sentimen Masyarakat Terhadap Produk Lokal Di Indonesia

“…Preprocessing dalam sebuah analisis sentimen merupakan tahapan yang tidak bisa ditinggalkan pada proses mining, hal ini dikarenakan data yang digunakan pada proses penambangan data tidak semuanya dalam kondisi bisa diproses. Penelitian (Sihombing et al, 2021) melakukan klasifikasi pada ulasan online terhadap produk hp yang diperjual belikan pada web Shopee di Indonesia menggunakan algortima Naïve Bayes, akurasi yang dihasilkan sebesar 85%, hasil ini belum bisa dikatakan optimal karena masih terdapat data misclassified. Hal ini bisa dijadikan acuan pada penelitian yang akan dilakukan perlu memperhatikan struktur dan metode pada tahap preprocessing agar kerusakan data seperti missing value, duplikasi, kesalahan system bisa diatasi.…”