ReMashed - Recommendations for Mash-Up Personal Learning Environments Hendrik Drachsler, Dries Pecceu, Tanja Arts, Edwin Hutten, Peter van Rosmalen, Hans Hummel & Rob Koper

What is ReMashed? A Mash-up environment that allows you to personalise emerging information of online communities with a recommender system. You tell what kind of Web 2.0 services you use and then you are able to define which contributions of other members you like and do not like.

A Mash-up environment that allows you to personalise emerging information of online communities with a recommender system.

You tell what kind of Web 2.0 services you use and then you are able to define which contributions of other members you like and do not like.

Goals for ReMashed End-User level Providing a recommender system for Web2.0 sources of learners in informal LNs Developer level Offering researchers a system for the evaluation of recommendation algorithms for learners in informal LNs Creating user-generated-content data sets for recommender systems in informal LNs

End-User level Providing a recommender system for Web2.0 sources of learners in informal LNs

Developer level

Offering researchers a system for the evaluation of recommendation algorithms for learners in informal LNs

Creating user-generated-content data sets for recommender systems in informal LNs

How does it work? ReMashed uses collaborative filtering to generate recommendations. It works by matching together users with similar tastes (neighbours) on different Web 2.0 resources (delicious, Flickr, blog feeds, Slideshare, Twitter, and YouTube).

ReMashed uses collaborative filtering to generate recommendations.

It works by matching together users with similar tastes (neighbours) on different Web 2.0 resources (delicious, Flickr, blog feeds, Slideshare, Twitter, and YouTube).

How does it work? Cold-Start = Tag-based recommendation Collaborative Filtering with ratings

How can you use it? Register at remashed.ou.nl Enter your favorite Web 2.0 Potatoes. Join the community. ReMashed starts mashing. Taste your personal flavor of Web 2.0.

The 1 st Release

The 1 st Release Database of Items User Interface PHP Algorithms

The 2 nd Release

The 2 nd Release Database of Items User Interface DUINE Prediction Engine

Detailed System Overview

New Interface Features Provided recommendations can be rated now and removed from the list of recommended items by a black star function. An explanation why a item is recommend is also added to the interface. Besides specifying accounts for different Web2.0 services the learners can specify three main ‘Interests‘ (learning goals) supported by an auto-completion algorithm that is fed with learning goals and tags of other community members. Further, they can indicate their knowledge level in the particular field of interests in a self-assessed way.

Future R&D Research Evaluation of new recommendation algorithms regarding their impact on learners in informal LNs Creation of various informal data set Development of a web service to offer recommendations to other Mash-Up PLEs additional PLE features to offer an attractive environment for participants of future experiments an administration layer to manage multiple instances of ReMashed communities (Knowledge sharing solution for organisations). a widget interface to ReMashed for the integration into PEs like iGoogle or Netvibes. recommendations via RSS feeds rating widget for emerging community data

Research

Evaluation of new recommendation algorithms regarding their impact on learners in informal LNs

Creation of various informal data set

Development of

a web service to offer recommendations to other Mash-Up PLEs

additional PLE features to offer an attractive environment for participants of future experiments

an administration layer to manage multiple instances of ReMashed communities (Knowledge sharing solution for organisations).

a widget interface to ReMashed for the integration into PEs like iGoogle or Netvibes.

recommendations via RSS feeds

rating widget for emerging community data

Many thanks for your interest! This slide is available here: http://www.slideshare.com/Drachsler Email: [email_address] Skype: hendrik.drachsler Blogging at: http://elgg.ou.nl/hdr/weblog Twittering at: http://twitter.com/HDrachsler