Using meaning instead of words to track topics
This addresses the need for businesses to monitor topic trends, but it is incremental as it introduces a new method without demonstrating clear superiority over existing ones.
The paper tackled the problem of tracking topic evolution over time by proposing a semantic-based method using word embeddings instead of lexical matching, and found that it performs comparably to lexical approaches but with different error patterns, suggesting potential complementarity.
The ability to monitor the evolution of topics over time is extremely valuable for businesses. Currently, all existing topic tracking methods use lexical information by matching word usage. However, no studies has ever experimented with the use of semantic information for tracking topics. Hence, we explore a novel semantic-based method using word embeddings. Our results show that a semantic-based approach to topic tracking is on par with the lexical approach but makes different mistakes. This suggest that both methods may complement each other.