Popular trends are predicted by leveraging the language of influencers as found in their electronic publications such as social media, blogs, etc. A list of influencers in a given field is curated along with a lexicon of the field which includes product names and associated modifiers. Natural language processing is performed on the current publications to identify a particular word combination based on syntactic relationships. The current usage frequency of the particular word combination is compared to a historical usage frequency derived from a baseline. If the current usage frequency is significantly higher, an alert is generated indicating that the particular word combination represents a candidate trend. The word combination may be a syntactic n-gram. The current usage frequency is based on a first, recent time window, and the historical usage frequency is based on a second time window preceding the first time window.
展开▼