This research focuses on the e-commerce market in Indonesia, which has experienced rapid growth and intense competition among various companies. Marketing intelligence is crucial for measuring competitive position, and customer satisfaction assessment is one element of marketing intelligence. Indonesian customers often express their satisfaction or dissatisfaction towards a company through social media, making it an essential source for measuring marketing intelligence efforts. This study uses sentiment analysis to determine customer satisfaction levels towards the top three e-commerce sites: Bukalapak, Tokopedia, and Elevenia. Twitter data was used for sentiment analysis due to its speed, cost-effectiveness, and ease of use from both the customer and researcher's perspective. The research aimed to process vast amounts of customer sentiment Twitter data into useful information for e-commerce companies while identifying which of the top three companies had the highest level of customer satisfaction. The text mining concept was used to analyze text patterns by analyzing text to obtain useful information for a specific purpose. Sentiment analysis was then applied to analyze people's opinions, sentiments, evaluations, appraisals, attitudes, and emotions on e-commerce as a product or service using naive bayes classifier with TF-IDF weighting. The training data consisted of 350 labeled negative texts and 350 labeled positive texts taken from each research object. Data was collected from Twitter using relevant keywords such as "Bukalapak," "Tokopedia," "Elevenia," "bukalapak_care," "tokopediacare," and "eleveniacare" during a week-long period in October 2016. A total of 69,598 tweets were collected but reduced to 2,974 after removing irrelevant tweets like advertising and spam during pre-processing. Pre-processing involved cleaning mined tweets by eliminating duplicates; removing URL links; filtering; removing unnecessary punctuation; tokenizing; stemming; stopword removal; case-folding; and preparing data for basic classification processes. The results showed that Elevenia had the highest level of customer satisfaction among the top three e-commerce sites. This research provides valuable knowledge and considerations for businesses, especially in the marketing intelligence field, using sentiment analysis to measure customer satisfaction levels towards products or services.
SummaryThis research is about online shopping in Indonesia. Three companies, Bukalapak, Tokopedia, and Elevenia were studied to see how happy their customers are. The researchers used Twitter to find out what people think about these companies. They found that Elevenia has the happiest customers. This information can help businesses understand how to make their customers happier.
Definitions
- E-commerce: buying and selling things online
- Marketing intelligence: information that helps businesses understand their competition and customers
- Sentiment analysis: using technology to figure out if people have positive or negative feelings about something
- Customer satisfaction: how happy or unhappy someone is with a product or service they received
- Social media: websites where people can share information and communicate with others online
- Naive bayes classifier with TF-IDF weighting: a way of analyzing data to find patterns in what people say
Understanding Customer Satisfaction Levels in Indonesia’s E-Commerce Market
The e-commerce market in Indonesia has experienced rapid growth and intense competition among various companies. To measure competitive position, marketing intelligence is essential, and customer satisfaction assessment is one element of this. Indonesian customers often express their satisfaction or dissatisfaction towards a company through social media, making it an invaluable source for measuring marketing intelligence efforts. This article will discuss a research paper that used sentiment analysis to determine customer satisfaction levels towards the top three e-commerce sites: Bukalapak, Tokopedia, and Elevenia.
Research Methodology
This study used Twitter data for sentiment analysis due to its speed, cost-effectiveness, and ease of use from both the customer and researcher's perspective. The research aimed to process vast amounts of customer sentiment Twitter data into useful information for e-commerce companies while identifying which of the top three companies had the highest level of customer satisfaction. The text mining concept was used to analyze text patterns by analyzing text to obtain useful information for a specific purpose. Sentiment analysis was then applied to analyze people's opinions, sentiments, evaluations, appraisals, attitudes, and emotions on e-commerce as a product or service using naive bayes classifier with TF-IDF weighting.
Data Collection
The training data consisted of 350 labeled negative texts and 350 labeled positive texts taken from each research object (Bukalapak; Tokopedia; Elevenia). Data was collected from Twitter using relevant keywords such as "Bukalapak," "Tokopedia," "Elevenia," "bukalapak_care," "tokopediacare," and "eleveniacare" during a week-long period in October 2016. A total of 69 598 tweets were collected but reduced to 2 974 after removing irrelevant tweets like advertising and spam during preprocessing.
Preprocessing
Preprocessing involved cleaning mined tweets by eliminating duplicates; removing URL links; filtering; removing unnecessary punctuation; tokenizing; stemming; stopword removal; case folding; and preparing data for basic classification processes.
Results & Conclusion
The results showed that Elevenia had the highest level of customer satisfaction among the top three e-commerce sites studied in this research paper. This research provides valuable knowledge and considerations for businesses who are looking at utilizing sentiment analysis techniques to measure customer satisfaction levels towards products or services they offer online in Indonesia’s highly competitive e-commerce market space .
The rapid growth of the e-commerce market in Indonesia, making various e-commerce companies appear and there has been high competition among them. Marketing intelligence is an important activity to measure competitive position. One element of marketing intelligence is to assess customer satisfaction. Many Indonesian customers express their sense of satisfaction or dissatisfaction towards the company through social media. Hence, using social media data provides a new practical way to measure marketing intelligence effort. This research performs sentiment analysis using the naive bayes classifier classification method with TF-IDF weighting. We compare the sentiments towards of top-3 e-commerce sites visited companies, are Bukalapak, Tokopedia, and Elevenia. We use Twitter data for sentiment analysis because it's faster, cheaper, and easier from both the customer and the researcher side. The purpose of this research is to find out how to process the huge customer sentiment Twitter to become useful information for the e-commerce company, and which of those top-3 e-commerce companies has the highest level of customer satisfaction. The experiment results show the method can be used to classify customer sentiments in social media Twitter automatically and Elevenia is the highest e-commerce with customer satisfaction.
