This interesting use, or not, of semantic technology caught my attention. Sometimes the accuracy of semantic analysis is in question and the topic in this specific situation could create even more suspicion. The students and professors at Humboldt State University avoided that by reading each of the 150,000 geo-coded tweets to produce a map revealing geographic differences in hate speech regarding, homophobia, racism, and specially challenged topics. The Guardian brought this interesting news to our attention in their article, “Mapping hate speech: homophobia and racism on twitter.”
By using humans instead of semantic analysis for this research, the researchers were able to ensure a higher level of quality and preciseness. This approach was interesting and the results equally so. Take time to look at the map. It is somewhat sobering.
Melody K. Smith
Sponsored by Access Innovations, the world leader in thesaurus, ontology, and taxonomy creation and metadata application.