Analysis and Monetization of Social Data Amit P. Sheth Lexis-Nexis Ohio Eminent Scholar Director,...

Analysis and Monetization of Social DataAmit P. ShethLexis-Nexis Ohio Eminent ScholarDirector, Kno.e.sis Center, Wright State University

222 MILL

ION

FACEBOOK

USERS 4000000 twitter users

3 Million tweets a day52,000 F8 APPLICATIONS

AND COUNTING

Intents in User Activity Elsewhere

June 01, 2009

What why and how people write

Cultural Entities

Word Usages in self-presentation

Slang sentiments

Intentions

Work and Preliminary Results in…

• Identifying intents behind user posts on social networks

• Pull UGC with most monetization potential

• Identifying keywords for advertizing in user-generated content

• Interpersonal communication & off-topic chatter

Identifying Monetizable Intents• Scribe Intent not same as Web Search Intent1

• People write sentences, not keywords or phrases

• Presence of a keyword does not imply navigational / transactional intents

• ‘am thinking of getting X’ (transactional)

• ‘i like my new X’ (information sharing)

• ‘what do you think about X’ (information seeking)

1B. J. Jansen, D. L. Booth, and A. Spink, “Determining the informational, navigational, and transactional intent of web queries,” Inf. Process. Manage., vol. 44, no. 3, 2008.

From X to Action Patterns

• Action patterns surrounding an entity

• How questions are asked and not topic words that indicate what the question is about

• “where can I find a chotto psp cam”

• User post also has an entity

Off topic noise – topical keywords

• Google AdSense ads for user post vs. extracted topical keywords

8X Generated Interest

• Using profile ads• Total of 56 ad impressions• 7% of ads generated interest

• Using authored posts• Total of 56 ad impressions• 43% of ads generated interest

• Using topical keywords from authored posts• Total of 59 ad impressions• 59% of ads generated interest

and then there is

space (where)

time (when)

theme (what)

twitris: spatio-temporal integration of twitter data “surrounding” an event

http://twitris.dooduh.com

Studying social signals

What is new and interesting?

What’s a region paying attention to today? What are people most excited or concerned about?

Why an entity’s perception changing over time in any region?

Image Metadatalatitude: 18° 54′ 59.46″ N, longitude: 72° 49′ 39.65″ E

Image Metadatalatitude: 18° 54′ 59.46″ N, longitude: 72° 49′ 39.65″ E

Geocoder (Reverse Geo-

coding)

Geocoder (Reverse Geo-

coding)

Address to location database

Address to location database

18 Hormusji Street, Colaba

Nariman House

Identify and extract information from tweets

Identify and extract information from tweetsSpatio-Temporal AnalysisSpatio-Temporal Analysis

Structured Meta Extraction

Structured Meta Extraction

Income Tax Office

Vasant Vihar

domain models to enhance thematic

relationships

who creates?

I will, you will, WE will

More at library@Kno.e.sis: http://knoesis.orgA. Sheth, "A Playground for Mobile Sensors, Human

Computing, and Semantic Analytics", IEEE Internet Computing, July/August 2009, pp. 80-85.

M. Nagarajan, K. Baid, A. P. Sheth, and S. Wang, "Monetizing User Activity on Social Networks - Challenges and Experiences“, 2009 IEEE/WIC/ACM International Conference on Web Intelligence WI-09, Milan, Italy

M. Nagarajan, et al. Spatio-Temporal-Thematic Analysis of Citizen-Sensor Data - Challenges and Experiences, Web Information Systems Engineering- WISE-2009, Poznan, Poland (to appear).

http://knoesis.org/research/semweb/projects/socialmedia/