Analyzing search queries to determine a user affinity and filter search results
View Patent ↗According to embodiments of the present invention, machines, systems, computer-implemented methods and computer program products for retrieving information pertaining to an affinity of a user are provided. In some embodiments, a search query is received from a user. The search query is analyzed to determine a bias of the user. The social media activity of the user is evaluated to determine affinity indicators for the user. Prior searches and selection of search results by the user is evaluated to detect patterns of the user. An affinity of the user is determined based on the bias, affinity indicators, and patterns. Initial search results are generated that satisfy the search query, and the initial search results are filtered based on the determined affinity of the user to produce search results in accordance with the determined affinity of the user.
1. A method of processing a search query comprising:
receiving a search query from a user;
analyzing, by a processor, query terms of the search query to determine a bias of the user based on the analyzing;
validating, by the processor, the determined bias of the user by:
evaluating social media activity of the user to determine affinity indicators for the user, and
examining prior searches and selection of search results by the user to detect patterns of the user;
determining, by the processor, an affinity of the user based on the determined bias, the determined affinity indicators, and the detected patterns; and
generating, by the processor, initial search results satisfying the search query and filtering the initial search results based on the determined affinity of the user to produce search results in accordance with the determined affinity of the user.
2. The method of claim 1 , wherein the analyzing the query terms of the search query includes:
analyzing the query terms of the search query by one or more from a group of natural language processing, semantic analysis, and sentiment analysis.
3. The method of claim 1 , wherein the evaluating the social media activity of the user includes:
evaluating the social media activity of the user by one or more from a group of natural language processing, semantic analysis, and sentiment analysis.
4. The method of claim 1 , wherein the social media activity includes one or more from a group of visited web sites, comments, likes, channel subscriptions, others followed by the user on social media, and others following the user on social media.
5. The method of claim 1 , wherein the determined affinity includes a positive affinity of the user toward an entity.
6. The method of claim 1 , wherein the determined affinity includes a negative affinity of the user toward an entity.
7. The method of claim 1 , wherein the bias of the user is further determined based upon the social media activity, the prior searches and the selection of the search results.