Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Techno Nusa Mandiri : Journal of Computing and Information Technology

SENTIMENT ANALYSIS ON TWITTER SOCIAL MEDIA ACCOUNTS: SHOPEECARE USING NAIVE BAYES, ADABOOST, AND SVM(EVOLUTION) ALGORITHM COMPARATIVE METHODS Rizky Nugraha Pratama; Ghina Amanda Kamila; Kresna Lazani T; Ilham Fauzi; Muhammad Reynaldo Oktaviano; Dedi Dwi Saputra
Jurnal Techno Nusa Mandiri Vol 19 No 1 (2022): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v19i1.3086

Abstract

The growth of Indonesian e-commerce is increasing along with the growth of internet use in Indonesia. In 2015, there were 92 million internet users in Indonesia. One of the popular online shopping platforms in Indonesia is Shopee. One of the services to see the response and reporting of problems from users, including shopeecare. shopeecare was created on the social media platform twitter to help facilitate communication between customers. with the amount of customer enthusiasm in tweeting and Retweeting existing content, we decided to research about Sentiment analysis on twitter social media accounts: Shopeecare uses the SMOTE NB, ADboost, and SVM comparison methods. From the data, the comparison results from the test experiments used the Smote + Naive Bayes, Smote + Naive Bayes + Adaboost, and Smote + SVM models. It is known that the Accuracy, Precision, AUC values of the Smote + SVM algorithm are higher than other algorithms, namely Accuracy 76.24%, Precision 75.65%, AUC 0.822. From the results of the algorithm comparison, it shows that the algorithm in determining the sentiment of the complaint and not complaint analysis is better than other algorithms.
COMPARING ALGORITHM FOR SENTIMENT ANALYSIS IN HEALTHCARE AND SOCIAL SECURITY AGENCY (BPJS KESEHATAN) ASYHARUDIN ASYHARUDIN; Novi Kusumawati; Ulfah Maspupah; Destia Sari R.F.; Amir Hamzah; Duwik Lukito; Dedi Dwi Saputra
Jurnal Techno Nusa Mandiri Vol 19 No 1 (2022): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v19i1.3167

Abstract

Twitter is a social media that can be used to express opinions and exchange information quickly with individuals and institutions such as the Healthcare and Social Security Agency (BPJS Kesehatan). Every word that a Twitter user utters has meaning and stellar emotion. This meaning can be reached through the process of sentiment analysis. Sentiment analysis is the process of understanding and classifying emotions such as positive or negative or complaining or not complaining. This study classifies tweet data related to BPJS Health services into two classifications, namely complain and no complain. Using 1,000 data from Twitter written on the BPJS Kesehatan Twitter account. In text mining, to build a classification, the transform case, tokenize, token filter by length, stemming and stopword techniques are used. Gataframework is used to assist the preprocessing and cleansing process. Rapidminer was used to create sentiment analysis in comparing three different classification methods of the Twitter data. The method used is the Nave Bayes algorithm and the Naïve Bayes algorithm with the addition of a Synthetic Minority Over-sampling Technique (SMOTE) feature and the Naïve Bayes algorithm with an SMOTE feature that is optimized with Adaboost. The Naïve Bayes algorithm is added with the SMOTE feature which is optimized with Adaboost to get the best value with an accuracy value of 69.11%, precision 69.93%, recall 68.89% and AUC 0.770