Welcome to Kalina's home page

Funding

Links

Support for Collaborative Learning and Collaborative Work: The main objective is to develop methods for supporting online learning communities because of the potential learning communities have for preparing for highly self-organised and life-long forms of learning and working, for creating new knowledge, and for creating social capital. Smart group support tools, including methods for user modelling and data mining, are used in order to optimise knowledge building and exchange. Empirical studies and experiments are conducted in order to identify successful cooperation patterns, including the selection of external representations and communication media.
This research addresses three objectives:
(1)    to identify, using various computational approaches, patterns of cooperation and media usage that distinguish successful from less-successful groups
(2)    to create visual representations of such patterns in a manner that can be used as feedback for groups, and to analyse the effects of such feedback on group performance,
(3)    to use the patterns identified in (1) to derive group- and person-specific guidance, and to test the effectiveness of this approach.

ARC-funded work with Judy Kay (School of IT), and Peter Reimann & Peter Goodyear (Faculty of Education).

Educational Data Mining: Web-based educational systems collect tremendous amount of electronic data, ranging from simple histories of students' interactions with the system to detailed traces about their reasoning. However, less attention has been given to handling the large quantities of data collected from the students' interactions and extracting pedagogically useful information from it. Such systems give teachers and learning researchers access to an extensive source of electronic data about students' learning, data which is currently under-exploited. Data mining techniques have the potential to remedy this situation. Data mining is a multidisciplinary sub-field of computer science combining work from several areas such as artificial intelligence, databases, statistics and information visualization. It encompasses a range of techniques and algorithms for discovering interesting patterns hidden in large data sets such as association analysis, classification, cluster analysis as well as statistical analysis and database query. In this project, the goals are:

To identify, adapt or create new data mining methods that are suited for turning learners' performance data into information of relevance to teachers, instructional designers, and learning researchers.
To define how to prepare and analyse the student data so that we can extract interesting patterns
To automate/facilitate some of the algorithm selection and pre-processing features
To find suitable ways to present the results to users
To exploit the patterns found to improve adaptation of teaching systems.

We have several threads of projects within this area. I work in collaboration with:

Peter Reimann (Faculty of Education, Computer-supported Learning and Cognition (CoCo) Unit) and Judy Kay (School of IT): Analyzing and supporting collaboration management in online learning communities. I also collaborate with Osmar Zaïane (University of Alberta, Canada) on data mining problems.
Judy Kay and Irena Koprinska (School of IT): data mining of learner models.
Agathe Merceron (Beuth University of Applied Sciences, Berlin, Germany): mining of student mistakes from the Logic Tutor; design of TADA-Ed, a Tool for Advanced Data Analysis for Education.

Student Modelling, tools for reflection: collaboration with Judy Kay on personalisation, we built viewable individual models and comparative models, with work by David Vadas on the Logic Tutor user model viewer.

Logic Tutor (with Agathe Merceron) and the Logic-ITA (see my publications)
Tada-Ed
Search Tutor
JITT: Just-in-time training system using workflows and scrutable personalisation

ARC Discovery Project grant 2009-2011: "Comprehensive support for collaborative writing: Visualising argument, text and process structures”. Reimann, Calvo, Yacef (270K).
ARC Discovery Project grant: 2005-2007. “Analyzing and supporting collaboration management in online learning communities”. Reimann, Goodyear, Kay, Yacef ($200,000).
USYD Bridging Support grant 2007: "Mining user models of learner activity in the Reflect system", Yacef, Kay, Koprinska, $15,000).
USYD Bridging Support grant 2006: "Data mining of learner models”. Yacef, Kay, Koprinska, Brusilovsky and Zaiane ($36,300)
SIT CRC project grant 2005-2007: “Bridging the Gap: Smart Support for the Intergenerational Distributed Family”. Kummerfeld, Kay, Yacef, Koprinska, Poon. ($270,000).
School of IT 2004-2005: “Extracting patterns from student data in web-based intelligent tutoring systems”, Yacef ($15,000).
School of IT 2004-2005: “Evaluating the educational usability of data mining and visualization of students' results in web-based learning systems”, Yacef, Reimann ($10,000).
SESQUI R&D grant: 2004. “User controlled personalisation in a system for tutoring logic”, Kay, Yacef, Kummerfeld ($20,000).
SITCRC project grant: 2002-2003. “Workflow based just-in-time workplace Training”, Kay, Davis, Yacef ($190,000).
Sesqui Early Career grant: 2001, “Providing an Intelligent Tutoring Aid to assist undergraduate teaching”, Yacef ($19,000).