Aspect-based Sentiment Analysis on Car Reviews Using SpaCy Dependency Parsing and VADER

All businesses, including car manufacturers, need to understand what aspects of their products are perceived as positive and negative based on user reviews so that they can make improvements for the maintain already products. One available tools this task is Sentiment Analysis. The traditional document-level sentence-level sentiment analysis will only classify each document / sentence into a class. This approach incapable finding more fine-grained specific aspect interest, example, comfort, price, engine, paint, etc. Therefore, in case, Aspect-based Analysis used. A total 22.702 rows review data scraped from Edmunds website (www.edmunds.com) manufacturer. Dependency Parsing noun phrase extraction were carried out using SpaCy module Python, VADER was used determine polarity phrase. Results showed vast majority sentiments aspects: comfortable drive, good fuel economy mileage, reliability, spaciousness, value money, helpful rear camera, quiet ride, acceleration, well-designed, sound system, solid build. results have some similar with those class but has very low frequency. means users satisfied multiple produced cars. limitation research future direction discussed.