A Sentiment Analysis about The Acquisition and Policy of X (Twitter) by Elon Musk

Adelia Fatimatuzzahro, Aisyah Larasati, Anik Dwiastuti — Fri, 18 Jul 2025 03:56:10 +0000

Social media Twitter (now X) is quite popular because it offers the ability to communicate between users and accelerate the flow of information obtained. In its development, the acquisition of the company by Elon Musk led to various changes. Some of the new policies had a direct impact on users and caused mixed reactions. This research applies a comparison between the two types of labeling techniques using TextBlob and VADER, a comparison of algorithms using Random Forest and Balanced Random Forest, as well as the use of algorithm parameters by default and Grid Search, to find information on user perceptions of the impact of the acquisition and new policy X by conducting sentiment analysis. The data used is the result of crawling X's post in the period from the emergence of the acquisition issue until the rebranding of the Twitter name and logo to X, namely April 25, 2022 to July 23, 2023. The results show that visually, these three factors have an accuracy level that shows the use of superior factors, namely TextBlob, Balanced Random Forest, and default parameters, whose combination obtained the highest accuracy value of 87%. The results of sentiment classification using two labeling techniques show that positive sentiment is greater than negative sentiment. However, in negative sentiment there are several problems based on the highest frequency of words that appear. So in this study, several recommendations are given that can be done to meet the expectations of user satisfaction with the X platform.

Grouping of Student Achievement Based on Student Names in Class VII of SMPN 28 Sarolangun Using the K-Means Clustering Method

Nur Chintia Ningsih, Dony Novaliendry, Yeka Hendriyani, Delvi Asmara — Fri, 18 Jul 2025 04:37:24 +0000

Although the selection of outstanding students is important to provide awards and recognition for student achievement, the methods currently used by schools are not optimal. The process often takes a long time and requires a lot of manpower to collect and process student data, which can ultimately disrupt daily school operations. This study aims to identify outstanding students in class VII at SMP 28 Sarolangun using the clustering method with the K-Means algorithm. This type of research is quantitative research. The method used in this study is K-Means Clustering , with the determination of the optimal number of clusters using the Elbow Method. The results of the study obtained a grouping of students into four clusters, including Cluster 1 with 10 students (15.2%), Cluster 2 with 16 students (24.2%), Cluster 3 with 25 students (37.9%) and Cluster 4 with 15 students (22.7%). From the resulting Elbow graph, the elbow point is seen at the value of K = 4, which indicates that four clusters are the most effective and efficient number to separate student data into meaningful groups.

Jurnal Teknologi Informasi dan Pendidikan

A Sentiment Analysis about The Acquisition and Policy of X (Twitter) by Elon Musk

Grouping of Student Achievement Based on Student Names in Class VII of SMPN 28 Sarolangun Using the K-Means Clustering Method