Analisis Sentimen Akun Twitter Apex Legends Menggunakan VADER

Abstract

Abstrak - Pesatnya peningkatan jasa internet saat ini, ada banyak informasi yang dihasilkan dalam jumlah besar secara terus menerus dalam waktu yang singkat. Akhir-akhir ini, analisis sentimen dengan menggunakan ulasan dan pesan telah menjadi topik penelitian yang populer dibicarakan di bidang Natural Language Processing. Selama bertahun-tahun, permainan online telah menjadi suatu aktivitas yang tidak bisa dipisahkan dari sebagian besar orang. Apex Legends adalah salah satu contoh game yang sangat popular di seluruh dunia. Untuk mendapatkan informasi bagaimana pendapat para pemain tentang permainan ini diperlukan analisis sentimen. Pada penelitian ini dilakukan analisis sentimen menggunakan bantuan aplikasi Orange Data Mining dengan metode VADER pada akun twitter Apex Legends menggunakan data sebanyak 500 tweet. Pengujian data dilakukan dengan membandingkan hasil yang didapat menggunakan metode VADER dengan hasil pengujian pakar, yaitu native speaker dari Canada dan Amerika. VADER mengklasifikasikan data yang didapatkan melalui twitter berdasarkan nilai compound yang didapat. Penelitian ini menghasilkan kesimpulan yaitu perbandingan dari pengujian menggunakan VADER dan pengujian pakar tidak berbeda jauh, yang mana total persentase dari penggunaan metode VADER untuk menganalisis sentiment dari twitter ini adalah : Positif = 18%, Negatif = 4,6%, Netral = 73,6%. Sedangkan hasil pengujian pakar adalah : Positif = 27%, Negatif = 10,8%, Netral = 62,2%.Kata kunci: VADER, Apex Legends, Game, Twitter, Uji Pakar Abstract - With the rapid increase in internet services today, there is a lot of information produced in large quantities continuously in a short time. Recently, sentiment analysis using reviews and messages has become a popular research topic discussed in the Natural Language Processing field. Over the years, online gaming has become an activity that cannot be separated from most of the people. Apex Legends is one example of a game that is very popular around the world. To get information on how the players think about the game, sentiment analysis is needed. In this study, sentiment analysis was carried out using the Orange Data Mining application with the VADER method on the Apex Legends twitter account using 500 tweets (data). Data testing is done by comparing the results obtained using the VADER method with the results of expert testing, native speaker from Canada and America. VADER classifies the data obtained through twitter based on the compound value obtained. This study concludes that the comparison of testing using VADER and expert testing is not much different, where the total percentage of using the VADER method to analyze sentiment from Twitter is : Positive = 18%, Negative = 4,6%, Neutral = 73,6%. While the results of expert testing is : Positive = 27%, Negative = 10,8%, Neutral = 62,2%.Keywords : VADER, Apex Legends, Game, Twitter, Expert Test (Uji Pakar)

Sentiment Analysis Regarding Kanjuruan Stadium Polemics Based on Public Opinion Through Twitter Social Media with SVM Classifier Method

“…1. Valence-aware dictionary and Sentiment Reasoner (VADER) is a method used as a model for sentiment analysis and can determine the diversity of data through the intensity of emotional power that exists according to the available Lexicon data dictionary (Abimanyu, 2022). VADER was introduced in 2014 by C.J Hutto and Eric Gilbert whose formation method is based on a human-centric approach, combining qualitative analysis and empirical validation using human wisdom and judgment (Mustaqim et al, 2020).…”

“…Sentiment can be categorized -such as {negative, neutral, positive} -or can be numerical -such as intensity range or score (Taboada et al, 2011). The lexical approach looks at the sentiment category or score of each word in a sentence and decides on the category or sentiment score of that whole sentence (Abimanyu et al, 2022) In this case, because the data taken is only positive and negative data, we will eliminate it first, so from the data taken from Twitter as many as 1183 for positive as many as 237, and negative as 658. 4, it is a confusion matrix model in a rapid-miner application using the SVM algorithm.…”

Perbandingan Analisis Sentimen Setelah Pilpres 2024 Di Twitter Menggunakan Algoritma Machine Learning

“…Salah satu keuntungan menggunakan pendeteksian polaritas VADER adalah tersedianya kamus yang mencakup nilai setiap kata. Apakah hasil preprocessing teks positif, negatif, atau neutral akan dinilai menggunakan lexicon, dan skor total (compound) akan ditambahkan [9].…”

Comparison of Naïve Bayes and SVM in Sentiment Analysis of Product Reviews on Marketplaces

“…This research employs the lexicon method for data labeling using the VADER dictionary designed specifically to detect sentiment in English text, containing 7,500 tokens. After going through the translation stage, VADER will function by invoking lexicon data from the NLTK server to calculate the polarity class of sentiment (Abimanyu et al, 2022).…”