Distributed Ledger (blockchain) technology provides an alternative for distributed databases. It creates a secure and immutable record of data transactions, thus tracking how data are shared and accessed. The access and operations on data can be regulated via "smart contracts" that allows setting conditions for accessing the data – by whom, for what purpose, for how long, under what conditions, whether access is granted to the original data or just a query /derivative data. In addition, users can benefit from sharing their data by using "smart contracts" that regulate sharing for monetary reward, or for another form of recognition. Both user profile data and user-owned data can be shared in this way, empowering users to benefit from their data, under their own conditions, rather than surrendering it to centralized services. The tutorial will present the basics of distributed ledger technology and smart contracts and will train the participants in using a privacy preserving user data-sharing framework.
The tutorial will present a new technology that allows privacy by design via distributed ledgers. The user has control on how her data is accessed and used, can benefit from the use of her data. The record of transactions over the user data is immutable and can be visualized, ensuring transparency/ scrutability not only of the user model but the way it is used – by whom, when, for what purpose, under what conditions. Privacy, control and scrutability of user models has been a long-standing goals for the User Modeling and Personalization community.
1 Introduction – why Blockchain for User Modeling?
2 Distributed Ledger - basic concepts
3 Smart contracts – what rules for access can be introduced; policies, templates
4 A Framework for sharing user data with smart contracts:
5 Practical sessions
5.1 Hands-on practice with Ethereum and Hyperledger
5.2 Building template smart contracts
5.3 Adapting the framework for sharing specific type of user data (in an example application)
Empirical Evaluation of User Modeling Systems (Beginner/3 hours), by Prof. David N. Chin (University of Hawaii).
This tutorial will introduce UM researchers to the techniques of empirical evaluation of user modeling systems. No background in statistics is required. The target audience is UM researchers, especially students, who have a background in computer science or some other field that does not normally include designing and running human-subject experiments. Topics include designing experiments (choosing independent/dependent variables, covariant and nuisance variables, between vs. within subjects designs, factorial designs, estimating sensitivity, layered evaluation), running experiments (recruiting participants, controlling the environment, recording data), data analysis (statistical tests, ANOVA, checking assumptions of statistical methods, explained variance), and common surveys/tests for gathering covariate data.
In this tutorial, participants will learn the basics of how to design experiment(s) to evaluate a user modeling system, how to run the experiment(s), and how to analyze the data gathered. To publish a journal or conference paper and sometimes even a workshop paper, empirical evaluation is required, yet the basics of how to do this is rarely taught in computer science departments, the most common background for UM researchers.
1 Experiment Design
1.1 Independent vs. dependent variables
1.2 Nuisance variables
1.3 Between-subjects vs. withinsubjects designs
1.4 Estimating sensitivity
1.5 Factorial designs
1.6 Layered Evaluation
2. Running Experiments
2.2 Controlling the environment
2.3 Recording data
3 Experiment Analysis
3.1 Means and variance
3.2 Statistical tests
3.4 Multiple testing correction
3.5 Explained variance
All rights reserved | Easy Conferences Ltd. - Easy CRS