Publication Search

The advancement of information and communication technology has significantly altered the ways adolescents interact and establish social relationships, particularly through social media. This study aims to examine the impact of human relations on adolescents' interactions and behaviors on social media platforms, taking into account psychological, sociological, and cultural dimensions. Employing a qualitative approach with a literature review method, this research explores interaction patterns among adolescents on platforms such as Instagram, TikTok, and Twitter. The findings reveal that social media creates virtual spaces that enhance social networks but also pose risks such as reduced quality of face-to-face interactions, social anxiety, and mental health issues. This study emphasizes how the intense use of social media reshapes traditional communication patterns and influences adolescents' behavior and self-concept. Based on these findings, strategic recommendations are proposed for parents, educators, and policymakers to guide healthy social media use, balance its benefits and drawbacks, and foster the development of more meaningful social relationships among adolescents.

This paper concerns the analysis of New Word Found on Twitter Using the Process of Word-Formation. The aim of this study is to analyze word-formation on words that have just appeared on social media, especially Twitter. The research used in this analysis is a qualitative research method. Source of research data in the study came from the Twitter app found in captions, comment fields, and retweet quotes. When collecting the data, the researchers used several steps, first searched the data in the Twitter app from captions, comment fields, and retweet quotes. Then, collect data containing word formation and classify the data by type. The data is collected and researchers analyze the type and process of word-formation. The results of this study indicate that there are 5 types of word-formation processes found on Twitter. They were derivation, abbreviation, blending, acronyms, and clipping. Of these types, abbreviations were the most common word-formation on Twitter.

Pada tahun 2024, Indonesia akan menyelenggarakan pemilihan umum serentak yang meliputi pemilihan presiden dan pemilihan wakil rakyat di seluruh Indonesia. Masyarakat menanggapi kejadian ini dengan perasaan campur aduk, membagikan pemikirannya di situs media sosial seperti Twitter. Penelitian analisis sentimen calon presiden Indonesia tahun 2024 dilakukan terkait peristiwa ini. Sebanyak 1458 tweet digunakan dalam penelitian ini. Dengan 40,31% responden menyatakan sikap positif dan 43,46% menyatakan sentimen negatif, temuan analisis menunjukkan keseimbangan antara kedua sentimen tersebut. Menggunakan frasa "calon presiden," program Python di situs web Google Colab mengambil data twitter. Pendekatan K-Nearest Neighbor digunakan dalam proses klasifikasi. Selain itu data latih dibagi 6 : 4. 40% data uji dan 60% data latih. Nilai evaluasi yang diperoleh dari pengujian model dengan teknik K-Nearest Neighbor adalah akurasi sebesar 90,95%, presisi sebesar 62,17%, recall sebesar 62,33%, dan F-Measure sebesar 61,87%.

According to the Jakarta Air Quality Index (AQI US) 12 July 2023, 200 indicates unhealthy air quality with an index value between 151 and 200. This figure even shows that Jakarta is currently the second most polluted city in Southeast Asia. (CNN Indonesia., 2023). This incident gave rise to responses from the public which were expressed via social media Twitter. From this incident, sentiment analysis was carried out regarding Jakarta's air quality. The amount of data used for this research was 500 tweet data. The results of the positive and negative sentiment analysis show that negative sentiment appears more frequently than positive sentiment with a percentage of 7% positive sentiment and 14% negative sentiment, by using the Rstudio application. This method uses the naïve Bayes classifier. Data division in the dataset with training data 1:499 and test data 1:476. It was found that the results of the Accuracy, Precision, Recall, and F1-Score values were Accuracy 87.50%, Precision 87.50 Recall 93.33%, and F1-Score 82.35%.