Citizen Sensing: Opportunities and Challenges in Mining Social Signals and Perceptions

Transcription

1 Wright State University CORE Scholar Kno.e.sis Publications The Ohio Center of Excellence in Knowledge- Enabled Computing (Kno.e.sis) Citizen Sensing: Opportunities and Challenges in Mining Social Signals and Perceptions Amit P. Sheth Wright State University - Main Campus, amit.sheth@wright.edu Follow this and additional works at: Part of the Bioinformatics Commons, Communication Technology and New Media Commons, Databases and Information Systems Commons, OS and Networks Commons, and the Science and Technology Studies Commons Repository Citation Sheth, A. P. (2011). Citizen Sensing: Opportunities and Challenges in Mining Social Signals and Perceptions.. This Presentation is brought to you for free and open access by the The Ohio Center of Excellence in Knowledge-Enabled Computing (Kno.e.sis) at CORE Scholar. It has been accepted for inclusion in Kno.e.sis Publications by an authorized administrator of CORE Scholar. For more information, please contact corescholar@

2 Citizen Sensing Opportunities and Challenges in Mining Social Signals and Perceptions Amit P. Sheth LexisNexis Ohio Eminent Scholar Ohio Center of Excellence in Knowledge enabled Computing (Kno.e.sis) Wright State University, Dayton, OH

3

4

5 BLENDED BROWSING & QUERYING Targeted e-shopping/e-commerce ATTRIBUTE & KEYWORD QUERYING assets access SEMANTIC BROWSING uniform view of worldwide distributed assets of similar type Taalee Semantic Search.

6 Semantic Search/Browsing/Directory (2001-.) Links to news on companies that compete against Commerce One Search for company Commerce One Crucial news on Commerce One s competitors (Ariba) Links to news on companies can be accessed easily and Commerce One competes against automatically (To view news on Ariba, click on the link for Ariba)

7 Semantic Search/Browsing/Directory (2001-.) System recognizes ENTITY & CATEGORY Relevant portion of the Directory is automatically presented.

8 Semantic Search/Browsing/Directory (2001-.) Users can explore Semantically related Information.

9 Semagix Freedom for building ontology-driven information system Managing Semantic Content on the Web

10

11 Domain Models Patterns / Inference / Reasoning Meta data / Semantic Annotations Metadata Extraction Relationship Web Search Integration Analysis Discovery Question Answering Situational Awareness RDB Structured and Semistructured data Text (formal/ Informal) Multimedia Content and Web data Sensor Data

12 Let Us Start with Social Data

13 Egypt Protest

14 Recently funded NSF proposal: Social Media Enhanced Organizational Sensemaking in Emergency Response Japan Earthquake and Tsunami

15 I-75 Traffic Jam in US

16 Citizen Sensing, Social Signals, and Enriching Human Experience Image:

17

18 Image:

19 Spatial, temporal, thematic: key phrase, named entity, relationship, topic/category, event descriptors, sentiment People, network, content core vocabularies/nomenclatures, community created dictionaries/folksonomies/reference databases, automatically extracted domain models, manually created taxonomies, formal ontologies

20

21 Spatio-Temporal-Thematic Analysis of Citizen-Sensor Data Challenges and Experiences Image:

22 TWITRIS

23

24

25

26

27 Image:

28 Collect topiccentric posts/messages in each time slice Collect network snapshots for this eventoriented community at the end of each time slice Extract the PCNA FEATURES (Content, People, Network) Classification for user engagement prediction problem Analyze the results and reason about specific user joining behavior 27 Understanding User-Community Engagement by Multi-faceted Features: A Case Study on Twitter

29

30 Event-Type Summary of Prediction Accuracy (%) Statistical significant results are in bold 29

31 Event oriented Community External Knowledge bases Dynamic Domain Model for the event SEMANTIC ASSOCIATION TO UNDERSTAND ENGAGEMENT LEVEL & IMPROVE IE Social Network Mined User Interests and User Types User Profiles

32 new new Multimodal Social Intelligence in a Real-Time Dashboard System

33

34

35

36 TWARQL

37

38

39 Continuous Semantics

40 Continuous Semantics dynamic domains

41

42

43

44 long long long must must

45

46

47 2010 s Real-Time Sensor, Social, Multi-media data 2000 s Dynamic User Generated Content 1990 s Static Document and files

48 Time 6pm 7pm 8pm 9pm Temperature 1(C) Rainfall (mm/h) Semantic Sensor Web Demo

49 48 Ohio Center of Excellence on Knowledge-Enabled Computing (Kno.e.sis) A cross-country flight from New York to Los Angeles on a Boeing 737 plane generates a massive 240 terabytes of data - GigaOmni Media But a pilot or a ground engineer at the destination is interested in very small number of events and associated observational data that are relevant to their work.

50 Background Knowledge Rain Storm Blizzard ABSTRACTION Huge amount of Raw Sensor Data Features representing Real-World events Semantic Sensor Web

51 Detection of events, such as blizzards, from weather station observations

52 Data Used: Nevada Blizzard (April 1 st April 6 th ) 70% Data clear 30% Feature Observed

53 Data Used: Nevada Blizzard (April 1 st April 6 th ) Semantic Scalability

54

55

56 Take Home Message Amount of citizen sensing (and machine sensing) data is huge, varied, and growing rapidly. Search and Sift won t work.

57 Take Home Message (Cont.) Semantics play a key role in refering "meaning" behind the data. Requires progress from keywords -> entities -> relationships -> events, from raw data to human-centric abstractions.

58 Take Home Message (Cont.) Wide variety of semantic models and KBs (vocabularies, social dictionaries, community created semistructured knowledge, domain-specific datasets, ontologies) empower semantic solutions. This can lead to Semantic Scalability scalability that is meaningful to human activities and decision making.

59 Kno.e.sis Wiki for the following and more: Computing for Human Experience Continuous Semantics to Analyze Real-Time Data Semantic Modeling for Cloud Computing Citizen Sensing, Social Signals, and Enriching Human Experience Semantics-Empowered Social Computing Semantic Sensor Web Traveling the Semantic Web through Space, Theme and Time Relationship Web: Blazing Semantic Trails between Web Resources SA-REST: Semantically Interoperable and Easier-to-Use Services and Mashups Semantically Annotating a Web Service Tutorial: Citizen Sensor Data Mining, Social Media Analytics and Development Centric Web Applications Partial Funding: NSF (Semantic Discovery: IIS: , Spatio Temporal Thematic: IIS ), AFRL and DAGSI (Semantic Sensor Web), Microsoft Research (Semantic Search) and IBM Research (Analysis of Social Media Content),and HP Researh (Knowledge Extraction from Community-Generated Content).

60