Web Analyst: Software for Solving Real-World Problems by Understanding Virtual Communities PI: Sun-Ki Chai (Dept. of Sociology) Co-PIs: David Chin (Dept. of Information & Computer Sciences) Scott Robertson (Dept. of Information & Computer Sciences) Mooweon Rhee (Dept. of Management and Industrial Relations) Min-Sun Kim (Dept. of Speech Communications) Jang Hyun Kim (Dept. of Speech Communications) Research Assistants: Kar-Hai Chu, Aaron Herres & Dong-Wan Kang United States Patent # 7499965 by Sun-Ki Chai
20
Embed
Web Analyst: Software for Solving Real-World Problems by Understanding Virtual Communities PI:Sun-Ki Chai (Dept. of Sociology) Co-PIs:David Chin (Dept.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Web Analyst: Software for Solving Real-World Problems by Understanding Virtual Communities
PI: Sun-Ki Chai (Dept. of Sociology)Co-PIs: David Chin (Dept. of Information & Computer Sciences)
Scott Robertson (Dept. of Information & Computer Sciences)Mooweon Rhee (Dept. of Management and Industrial Relations) Min-Sun Kim (Dept. of Speech Communications)
Jang Hyun Kim (Dept. of Speech Communications)
Research Assistants: Kar-Hai Chu, Aaron Herres & Dong-Wan Kang
United States Patent # 7499965 by Sun-Ki Chai
Current Research Supported by the Air Force Office of Scientific Research and the Office of Naval Research
Why the Need for Better Web Analysis Software?
The WWW is becoming the location for much of the world’s cultural, political and economic activity
Information on the web is mostly publicly available and can be collected with little cost, time, and intrusion.
Still, no general-purpose software tool exists for systematically collecting and analyzing data from the web to answer real-world questions about human attitudes and behavior.
To be effective, such a tool must be based upon cutting-edge social science theories and methods for locating, analyzing, and presenting relevant and accurate information.
What Kind of General Solutions WillThis Software Provide?
• Who is most interested in your product or issue?
• How do they feel towards this product or issue?– What other interests do members of this community have?
• Who are the most influential and powerful people in this community? – What are the characteristics that make them so?
• How do we associate an online community with a particular real-world location and group? – What will the future behaviors of that group be?
Web-Mining Software that Understands the Social Nature of the Web
• Integrates a wide range of validated social science theories on social networks, language, attitudes, culture, and behavior.
• Downloads and stores a full and customizable range of content, link, geographical, and traffic data.
• Includes specialized forums and blogs analysis and collection.
• Variety of interfaces allow customization of crawl, analysis, visualization, and output.
Starting Out: Locating the Right Virtual Community
• User enters a few “seed” sites to start the exploration.
• Control exactly how many sites to look for, how deep to go into each site, or select one of our pre-made profiles
The System at Work: Building a Virtual Community
• Our interface provides real-time feedback as it explores the web, including visual map and listing of the virtual community as it grows.
• System allows users to halt processing at any time, save the stage, and resume at a later point.
Specialized Exploration: The Forum Analyzer
• Forum– A message board or online discussion site
• Forum Analyzer – Measures activity level– Estimates the strength of community– Detects opinion and sentiment
0.00
0.50
1.00
1.50
2.00
2.50
SF1 SF2 Buick Civic Mac BrainTalk Autism
Mean Reply Depth
Participation Rate
Community Metrics in Forums
• Web metrics – Standard web traffic statistics and data
• Community metrics– Member interaction and communication structure– Response time, mean reply depth, active participation rate
Content Analysis: Contrast Between Different Kinds Forums
• Pronoun usage
– I, we, they
• Emotions– neg emotion,
anxiety, sadness, anger
0.00
1.00
2.00
3.00
4.00
5.00
6.00
7.00
8.00
SF1 SF2 DSM1 Civic Flu Lung
i
we
they
0.00
0.50
1.00
1.50
2.00
2.50
3.00
SF1 SF2 DSM1 Civic Flu Lung
negemo
anx
anger
sad
Analysis of Member Communication Networks in Forums
Centralized vs. Distributed
Application: Forum Analyzer
What The Technology Provides
Human behavior data based on established social science theories and metrics.
These can be freely composed, weighted, and added together in an intuitive way.
Content and network information combined seamlessly to provide the most accurate answers.
Features to be Implemented
Integration of specialized blog analysis features in partnership with ASU.
Specialized front-end modules for specific fields of inquiry, e.g. product marketing, predicting political opinion trends, violence and risk assessment.
Systematic comparison of data obtained from virtual communities to that from traditional surveys and experiments.
Integration with UH cultural change and behavioral modeling software
What Kind of General Solutions WillThis Software Provide?
• Locate the virtual community that best represents a social group of interest to the user.– Who are the people on internet who are most interested in a particular
product or issue?• Find out ideas and sentiments most prevalent within a community, and
predict how these will change over time.– What other interests do members of this community have?– In what ways is this community united/divided?
• Identify the most powerful and influential actors in a community and the characteristics that make them so.– Who are the opinion-makers that I should try to look at first?
• Predict the future behaviors of social groups from their online presence and identify emerging political and cultural movements. – Which political groups will translate their opinions into open conflict with
the government?• Provide a kind of "reverse search engine" that generates the most
important identifying characteristics of a community.
Web-Mining Software that Understands the Social Nature of the Web
• Integrates a wide range of validated social science theories on social networks, language, attitudes and culture, and behavior to identify and analyze those websites most relevant to user.
• Downloads and stores a full range of content, link, geographical, and visit data on these sites.
• Simple analysis for first-time users, and power interface that allows full customization of crawl, analysis, and output.
• Includes specialized tools for that recognize and perform enhanced data collection and analysis on forums and blogs.
• Real-time visual and data feedback as software explores and analyzes sites.
• Generated information is collected in data files that are easily integrated with popular third-party software for further analysis.
Features to be Implemented
Integration of specialized blog analysis features in partnership with ASU.
Wizard interface that allows user to specify a research question directly, then configures the crawl, analysis, and data formatting to best answer this question.
Implementation in both desktop and web application modes. Specialized front-end modules for specific fields of inquiry, e.g. product
marketing, predicting political opinion trends, violence and risk assessment.
Systematic comparison of data obtained from virtual communities to that from traditional surveys and experiments.
Integration with UH cultural change and behavioral modeling software to create forecast systems that can automatically collect the data they need to make their predictions.
Any requests?
Comments
Avoid embedded video, so may have play stand-alone – mpeg-1, wmv file
Went 40 minutes – part was discussion, but may need to paring things down
Less text on first three slides . . . more audience participation
Multiple people talking . . . OK
What would you take out – need to know what it can do, but not how it works
Me in particular need to be succinct – 7 minutes approx.
Can eat into your Q&A but this is not good.
Questions coming up – how do you differentiate troller from opinion leader?
More about what it does rather than how it does it . . .