Implicit aspect-based opinion mining and analysis of airline industry based on user generated reviews

Mining opinions from reviews has been a field of ever-growing research. These include mining opinions on document level, sentence-level, and even aspect level of a review. While explicitly mentioned aspects in a review have been widely researched, very little work has been done in gathering opinions on aspects that are <em><strong>implied </strong></em>and not explicitly mentioned. E.g. “<strong><em>the flight was spacious and there was plenty of legroom</em></strong>”. This gives an opinion on the <em><strong>entities </strong></em>of the <em><strong>cabin </strong></em>and <em><strong>seat </strong></em>of an airline. Words like “<strong><em>spacious</em></strong>” and phrases like “<strong><em>plenty of legroom</em></strong>” help identify these <em><strong>implied entities</strong></em> and the <strong><em>opinions </em></strong>attached to them. Not much research has been done for gathering such implicit aspects and opinions for airline reviews. The present dataset is a <em><strong>manually annotated domain-specific aspect-based corpus </strong></em>that helps a study to extract and analyze opinions about such implied aspects and entities of airlines.