Sentiment Analysis on Utilizing Online Transportation of Indonesian Customers Using Tweets in the Normal Era and the Pandemic Covid-19 Era with Support Vector Machine

Abstract

Online transportation in Indonesia is a new trend of transportation that is currently used among the lower to upper society. The change in behavior began in 2011 and is growing to this day, The comments that are growing on social media are very important for the online transportation company the negative comments lower the level of users while the good comments increase the users' level. Thus, the comments influence the overall trust of their customers. Among social media, Twitter is a place where many people convey feelings of pleasure and displeasure timely, especially at a time when the COVID-19 pandemic is becoming a serious outbreak. Through these "tweets," many customers express their experience with the service. In this paper, we aim to analyze the experience of online transportation consumers using Support Vector Machine. The data were taken in two periods, i.e. April 2019 ("the normal era") and June 2020 ("the COVID-19 pandemic outbreak. Class logging is done based on 3 categories namely positive, negative and normal, while in mining the data we labeled with the keywords @grabID and @gojekindonesia, 1618 data were obtained with a ratio of 1183 is normal era data and 435 data in the era of COVID-19 pandemic, The highest accuracy results occurred in the normal era with a ratio of 10% as test data and 90% as its training data on linear and sigmoid kernels of 0.8060 while the COVID-19 era only got the highest accuracy of 0.59 in linear kernels with a ratio of 60:40. This is a sign that the COVID-19 pandemic does not contribute to decreasing trust in the service.

IndoPolicyStats: sentiment analyzer for public policy issues

“…Twitter has been an enormous source of data about public responses. The experience of using Twitter made the public feel convenient about sharing their thoughts about anything on the platform, including their reaction to public policy, in this case, the Covid vaccination policy [13], [17]- [20]. Previous studies used social media data, specifically Tweets, to analyze public discourses and sentiments.…”

Sentiment Analysis of Electricity Company Service Quality Using Naïve Bayes

“…Then to be able to retrieve rating data, it is necessary to capture HTML and then apply an Aria Regular Expression (RegEx) label with the sentence before the star number, as shown in Figure 2. Tokenization method [18]. Data cleaning is required to remove unnecessary punctuation and delete Stop Words after the Tokenization process.…”

“…The class "Positive" denotes a positive user review, whereas the word "Negative" denotes a negative user review. Search engines typically evaluate or rate the degree of connection between documents and user queries using different TF-IDF weighting methods [18] so that after the text data has been successfully transformed into uniform and basic words, they start to weigh as much importance as words using the TF-IDF method. The Naïve Bayes technique will be used to do sentiment analysis on user comments or opinions to categorize the judgments they make about this series.…”

“…A shorthand for the terms "term frequency" and "inverse document frequency," respectively, is TF-IDF. The first topic to be covered deals with the term's frequency; TF is used to calculate how frequently a term appears in a text [18]. If we have a document named "Doc1" with 1500 words and exactly 10 instances of the word "Good," we can use this as an example.…”

“…Second, we will talk about document frequency inversion. When the document term frequency is determined, the algorithm evaluates every keyword similarly, regardless of whether it is a stop word like "from," which means it may be inaccurate [18]. Varying keywords have different weights.…”