Tacit Knowledge Mining John Canny Computer Science Division UC Berkeley.

Slides:



Advertisements
Similar presentations
Data Mining and the Web Susan Dumais Microsoft Research KDD97 Panel - Aug 17, 1997.
Advertisements

_________________________ Jacqueline M. Hughes-Oliver North Carolina State University, Statistics SAMSI CDI Workshop November 1, 2007 Panel on Building.
A platform of for knowledge and services sharing Fernando Ferri IRPPS-CNR.
1.Accuracy of Agree/Disagree relation classification. 2.Accuracy of user opinion prediction. 1.Task extraction performance on Bing web search log with.
Servicing 'Core' and 'Chore': A framework for understanding a Modern IT Working Environment David Harrison and Joe Nicholls Cardiff University.
McGraw-Hill/Irwin © 2008 The McGraw-Hill Companies, All Rights Reserved Chapter 15 Creating Collaborative Partnerships.
BUSINESS DRIVEN TECHNOLOGY Enhancing Collaborative Partnerships
Collaboration and Learning The perspective of a Cluster.
Distributed Collaboration for Whole of Society Crisis Response (WoSCR) Jeff Hansberger, Ph.D. Army Research Laboratory SL: Jeff Reanimator.
Context-Aware Computing John Canny HCC Retreat 7/5/00.
Community of Science The Leading Internet Site for Researchers Worldwide
Human-Centered Computing Long-range plan John Canny UC Berkeley.
Securing Organizational Knowledge using Automated Annotation Savitha Kadiyala K.R. Namuduri Venu Dasigi.
KNOWLEDGE MANAGEMENT AT ACCENTURE
Human-Centered Computing Retreat Overview John Canny UC Berkeley.
Digital Library Service Integration (DLSI) --> Looking for Collections and Services to be DLSI Testbeds
Understanding Networked Applications: A First Course Chapter 2 by David G. Messerschmitt.
What is communication? What are the issues in interpersonal communication? What is the nature of communication in organizations? How can we build more.
Personalized Ontologies for Web Search and Caching Susan Gauch Information and Telecommunications Technology Center Electrical Engineering and Computer.
Libraries and Institutional Content Management Systems
The Institute for Triple Helix Innovation
BUSINESS DRIVEN TECHNOLOGY Chapter Fourteen: Enhancing Collaborative Partnerships.
Module 3: Business Information Systems Chapter 11: Knowledge Management.
Computer-mediated communication Acknowledgements to Euan Wilson (Staffordshire University)
Landing the Raven: Positioning the Knowledge Discovery System in the Enterprise Wendi Pohs, Iris Associates
Multimedia Specification Design and Production 2013 / Semester 2 / week 7 Lecturer: Dr. Nikos Gazepidis * Notes by Dr Trevor Baker.
Digital Content Creation and Processing in the Context of Digital Culture and Cultural Heritage Digitalisation Cultural Heritage Digitalisation meeting.
Enterprise & Intranet Search How Enterprise is different from Web search What to think about when evaluating Enterprise Search How Intranet use is different.
Knowledge Management Systems Agnes Bui MIS /01/2004.
Fishing In an Ocean of Information
Chapter Intranet Agents. Chapter Background Intranet: an internal corporate network based on Internet technology. Typically, an intranet can.
Human Resource Management Lecture 27 MGT 350. Last Lecture What is change. why do we require change. You have to be comfortable with the change before.
University of Dublin Trinity College Localisation and Personalisation: Dynamic Retrieval & Adaptation of Multi-lingual Multimedia Content Prof Vincent.
1 KNOWLEDGE TRANSFER By Ellen Schwindaman 2 The Power is in Sharing the Knowledge Changing the behavior of knowledge holders is the biggest challenge.
1 Promoting Evidence-Informed Practice: The BASSC Perspective Michael J. Austin, PhD, MSW, MSPH BASSC Staff Director Mack Professor of Nonprofit Management.
Sharad Oberoi and Susan Finger Carnegie Mellon University DesignWebs: Towards the Creation of an Interactive Navigational Tool to assist and support Engineering.
Implicit An Agent-Based Recommendation System for Web Search Presented by Shaun McQuaker Presentation based on paper Implicit:
Knowledge Management …basic principles and practices.
Baker ONR/NETC July 03 v.4  2003 Regents of the University of California ONR/NETC Planning Meeting 18 July, 2003 UCLA/CRESST, Los Angeles, CA ONR Advanced.
인지구조기반 마이닝 소프트컴퓨팅 연구실 박사 2 학기 박 한 샘 2006 지식기반시스템 응용.
Personalized Interaction With Semantic Information Portals Eric Schwarzkopf DFKI
IP Taskforce Conference November 12, 2003 The KM Foundation for IP Capitalization By Doug Crews President Criteria First.
Finding Experts Using Social Network Analysis 2007 IEEE/WIC/ACM International Conference on Web Intelligence Yupeng Fu, Rongjing Xiang, Yong Wang, Min.
MIS 2000 Chapter 15 Knowledge Management. Outline Knowledge Explicit and Tacit Knowledge Knowledge Management Activities Computer-Aided Design/Manufacturing.
1 The UNCHIKU System A Platform for Collaborative Learning and Knowledge Development with Online Community Mitsuyuki Inaba College of Policy Science Ritsumeikan.
JISC/NSF PI Meeting, June Archon - A Digital Library that Federates Physics Collections with Varying Degrees of Metadata Richness Department of Computer.
IT and Network Organization Ecommerce. IT and Network Organization OPTIMIZING INTERNAL COLLABORATIONS IN NETWORK ORGANIZATIONS.
Fundamentals of Organization Structure
Visualizing Mailbox Yoo Ah Kim Min-ho Shin Department of Computer Science University.
Future research in KMS Huge potential… forever? How can you avoid over-promising? Organizations & culture must change in concert with KMS - A changed organization.
SSE3 Knowledge mangement concepts 1. Agenda What is knowledge management Classification of knowledge Knowledge management process Common/shared information.
UOS Personalized Search Zhang Tao 장도. Zhang Tao Data Mining Contents Overview 1 The Outride Approach 2 The outride Personalized Search System 3 Testing.
McGraw-Hill/Irwin © 2008 The McGraw-Hill Companies, All Rights Reserved Chapter 15 Creating Collaborative Partnerships.
1 Sharepoint 2010 MySite Sharepoint as a people platform Find and connect with people and knowledge Arild Aarnes ErgoGroup
1. IT Infrastructure Amna Riaz007 Tayaba Ashraf008 2.
Groupware What are the goals of a groupware system? - Facilitation - Coordination - Cooperation - Augmented, supported production Is efficiency the goal?
Intranets, Portals & Organizations System Evaluations Due Now Readings Review Book Reports Research Paper Discussion.
OntoZilla: An Ontology-based, Semi-structured, and Evolutionary P2P Network for Information Systems and Services 指導教授:李官陵 學 生:陳建博 蔡英傑
1 Senn, Information Technology, 3 rd Edition © 2004 Pearson Prentice Hall Information Technology, 3 rd Edition Chapter 1 Information Technology: Principles,
Working with Individual and Organizational Knowledge Introduction.
Records Coordinator Roles and Records Skills Kathryn Dan.
CHAPTER TEN OVERVIEW SECTION ENTERPRISE RESOURCE PLANNING
Creating Collaborative Partnerships
Our Digital Showcase Scholars’ Mine Annual Report from July 2015 – June 2016 Providing global access to the digital, scholarly and cultural resources.
Contextual Intelligence as a Driver of Services Innovation
Agents & Agency What do we mean by agents? Are agents just a metaphor?
CHAPTER TEN OVERVIEW SECTION ENTERPRISE RESOURCE PLANNING
An ecosystem of contributions
Web Mining Department of Computer Science and Engg.
Presentation transcript:

Tacit Knowledge Mining John Canny Computer Science Division UC Berkeley

UCB HCC Motivation People often collaborate across geographic, cultural and disciplinary boundaries. Workgroups are more short-lived today. There is less time to learn each other’s skills sets, to develop trust, and a “voice” within the group. On the other hand, there is a wealth of information available in groupware systems about people’s interactions with each other and with data.

UCB HCC An opportunity We know that much of the useful knowledge in a group or organization is “tacit”. Can we recover and use tacit knowledge? Human knowledge and knowhow is difficult and expensive to codify. But the knowledge encoded in activity data may be less so. Examples: expertise discovery, group structure, document dependencies.

UCB HCC Platform: Lotus Notes for now Data sources:  Direct messaging: sender, receiver, time, duration..  Topical discussions or threaded .  Document access (by links or directories)  Document search (by text queries)  Annotations on documents.

UCB HCC Analysis methods: Social Networks. Centrality measures for estimating authority and prestige.

UCB HCC Analysis methods: Clustering. Discovering tacit groups, and related sets of documents. Classification. Use a knowledge hierarchy to classify documents, and compute expertise profiles.

UCB HCC What we want to assist: Expertise discovery. Expertise profiles include authority in each area. Document access. We compute document authorities and use them in ranking. Group dynamics. Does the communication network contain any problematic structures?

UCB HCC What we want to assist: Sensemaking, document context. Record the document creation process. Prioritize records. Attention management. Infer a current task and adjust awareness of documents and other people according to their proximity to the task. Perspectives. Organize annotations (when available) on a document according to the expertise of author and annotator.