Automotive brand’s products

The data used in this study consists of Twitter posts (tweets) related to an automotive brand’s products. The dataset was collected through web scraping using the Twitter API, based on specific keywords such as the brand name and the models of the vehicles being analyzed.

Each record in the dataset includes the text content of the tweet, the posting date, the number of likes and retweets, and limited user metadata such as location (when available) to provide geographical context for public opinions. The data was collected over a defined time period to capture the most recent consumer perceptions toward the automotive brand’s products.

Prior to analysis, the dataset underwent several preprocessing steps, including text cleaning (removing URLs, punctuation, and mentions), normalization, tokenization, and stopword removal to ensure that the data was suitable for sentiment analysis.

The primary objective of using this dataset is to identify and classify user opinions about the automotive products into three sentiment categories: positive, negative, and neutral. The analysis aims to provide insights into consumer perception, emerging public opinion trends, and specific product aspects that attract the most attention on social media.