Abstract
The current dataset is obtained by text mining of β-hydroxybutyrate (BHB) supplement products’ consumer online reviews. The text data of 71 BHB products’ consumer reviews were extracted with the aid of the Web Scraper Chrome extension. Then, a lexicon-based sentiment analysis approach was developed to classify the sentiment or polarity of BHB products’ consumer reviews. Both word-level and sentence-level sentiment analyses were conducted to score the analyzed text snippets. In terms of word-level sentiment analysis, word clouds of selected BHB products’ reviews were generated to give direct observation, and the statistics of high-frequent sentiment words were listed for comparison. In terms of sentence-level sentiment analysis, two factors such as flavor and package were taken into consideration to map the products' polarity distributions. Besides, the complex analysis provides us with the basic statistics of the analyzed BHB customer reviews data.
Highlights
The current dataset is obtained by text mining of βhydroxybutyrate (BHB) supplement products’ consumer online reviews
In terms of word-level sentiment analysis, word clouds of selected BHB products’ reviews were generated to give direct observation, and the statistics of high-frequent sentiment words were listed for comparison
Negative, neutral, and compound scores were assigned to the analyzed text snippets through sentiment analysis
Summary
The text data of β-hydroxybutyrate (BHB) products’ customer reviews were collected from. Amazon.com with the aid of the Web Scraper, a Chrome extension. Sometimes require pre-process or cleaning before text mining to minimize the noises or bias [6]. For the reviews in this research, most users express their comments in a brief and straightforward way. There are not many noise and uninformative parts as HTML tags, scripts and advertisements as other online texts [6]. We cleaned the text data by removing special characters and reorganizing the content for further analysis. On another side, we tried maintaining the originality of the review contents as much as possible
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
