Concept-level user intent profile extraction and applications
Methods and systems for extracting intents and intent profiles of users, as inferred from the different activities they execute and data they share on social media sites, and then (i) monetization of such intents via targeted advertisements, and (ii) enhancement of user experience via organization of their contact lists and conversations and posts based on their content and conceptual context.
1. A computer-implemented method comprising:
identifying, via a processor, structured user data from a social media site, the structured user data comprising an email identification, phone number, geo-location, friends and links;
identifying, via the processor, user activities exclusively on the social media site;
identifying, via the processor, incoming likes, sharing, recommendations on the social media site;
identifying, via the processor, connections of the user;
identifying, via the processor, user activities involving the Internet that do not involve the social media site;
identifying, via the processor, user searches that do not involve the social media site;
obtaining a global concept graph comprising nodes that are concepts, and edges that are relationships among such concepts, wherein the concepts comprise phrases that represent entities, domain-specific terms and common expressions that are used to convey information; and
wherein the relationships are identified by annotated edges among concepts, wherein the relationships comprise measures of closeness among the concepts, including at least one of co-occurrence statistics and explicit semantic relationships;
obtaining at least one weighted sub-graph of the global concept graph using the structured user data; the user activities on the social media site; the user activities not involving the social media site; the incoming likes, sharing, and recommendations on the social media site; the user searches that do not involve the social media site; and the connections of the user;
obtaining an intent profile of the user from information in the weighted sub-graph(s); and
matching the intent profile with an advertiser profile to target an advertisement to the user.
2. The method of claim 1 further comprising:
generating a score for each vertical in a targeting vertical list.
3. The method of claim 2 , wherein the score comprises a time factor and an interest factor.
4. The method of claim 2 , wherein the score is generated based on user activities exclusively on the social media site, user activities involving the Internet, incoming likes, sharing, recommendation on the social media site, and user searches.
5. The method of claim 1 further comprising:
modifying a user experience of the user by organizing a contact list of the user and conversations and posts of the user based on their content and conceptual context.
6. The method of claim 5 , further comprising:
performing an aggregation scoring.
7. The method of claim 1 , wherein the concepts are selected from the group consisting of people, companies, drugs, diets, films, shows, events, wherein the domain-specific terms are selected from the group consisting of sports and medical terminologies, specific treatments, and procedures.
8. The method of claim 1 , further comprising tagging the intent profile of the user with temporal data.
9. The method of claim 1 , further comprising:
tagging unstructured data using collective activities of users at the social media site,
wherein the unstructured data is selected from searches, we-browsing, posts, comments, content of web pages that received Likes and links.
10. The method of claim 1 , further comprising:
prioritizing unstructured data using collective activities of users at the social media site.
11. The method of claim 1 , further comprising post-processing and tagging the intent profile of the user with weighted category scores defined over a structured taxonomy of interest.
12. The method of claim 1 , further comprising assigning at least one advertiser a set of advertiser target profiles.
13. The method of claim 12 , wherein each of the advertiser target profiles comprises a weighted list of categories picked from a structured taxonomy.
14. The method of claim 1 , wherein selecting a final set of advertisement units is completed by an optimization process that maximizes objective functions of interest, including revenue for the social media site, value and Return-On-Investment (ROI) for advertisers, while considering a device and media of the user.
15. The method of claim 5 , wherein modifying a user experience comprises organizing friends or contact lists of the user into potentially overlapping groups by computing similarity between a user's profile and the profiles of those of his friends and contacts.
16. The method of claim 15 , wherein organizing friends or contact lists of a user into potentially overlapping groups comprise computing similarity between a user's profile and the profiles of those of the user's friends and contacts.
17. The method of claim 5 , wherein modifying a user engagement comprises organizing posts, comments and social interactions between a user and his friends based on an underlying context.
18. The method of claim 17 , wherein a linear list of posts on page of the social media site can be organized into categories by automatically classifying the posts by mapping the posts to categories in the nodes and edges.
19. The method of claim 1 , further comprising post-processing and tagging the user profile with weighted category scores defined over a structured taxonomy of interest.
20. The method of claim 1 , further comprising determining a suggested search term based on the intent profile of the user.
21. The method of claim 1 , further comprising:
grouping content based on communal user actions; and
dividing the grouped content into clusters.
22. The method of claim 21 , further comprising:
generating a collective content profile.
23. The method of claim 22 , further comprising prioritizing the grouped content based on page and domain statistics.