PLEM - User Scenario

Our student Simona Dakova has created a sample user scenario for PLEM. More information about PLEM can be found here.

Please feel free to use this service. Comments, feedback, suggestions for improvement etc. are welcome!

PLEM: a Web 2.0 driven Long Tail aggregator and filter for e-learning

The paper "PLEM: a Web 2.0 driven Long Tail aggregator and filter for e-learning" has been published in the International Journal of Web Information Systems (IJWIS) by Emerald. A preprint of this paper can be downloaded here. The PLEM project homepage can be accessed here.

Abstract:

The Personal Learning Environment (PLE) driven approach to learning suggests a shift in emphasis from a teacher driven knowledge-push to a learner driven knowledge-pull learning model. One concern with knowledge-pull approaches is knowledge overload. The concepts of collective intelligence and the Long Tail provide a potential solution to help learners cope with the problem of knowledge overload. Based on these concepts, the paper proposes a filtering mechanism that taps the collective intelligence to help learners find quality in the Long Tail, thus overcoming the problem of knowledge overload. We present theoretical, design, and implementation details of PLEM, a Web 2.0 driven service for personal learning management, which acts as a Long Tail aggregator and filter for learning. The primary aim of PLEM is to harness the collective intelligence and leverage social filtering methods to rank and recommend learning entities.

Reference:

Chatti, M.A., Anggraeni, Jarke, M., Specht, M., and Maillet, K. (2010) ‘PLEM: a Web 2.0 driven Long Tail aggregator and filter for e-learning’, International Journal of Web Information Systems, Vol. 6, No. 1, pp. 5–23.

PLEM for Edublog Ranking

The poll for the Edublog Awards 2009 closed today. While waiting for the outcome of the voting, I tried to use the PLEM ranking algorithm to rank the nominated blogs in the category "Best individual blog" based on the Wisdom of Crowds and different interaction metrics (PLEM saves and ratings, Delicious saves, Friendfeed comments and likes, Yahoo inbound links, Digg votes, Google Trackbacks, and Technorati blog reactions). To see the result, you can visit the PLEM project Website here, hit the "edublog" tag from the "Popular Tags" list, and choose "Most Popular" as the ranking option. Below is a screenshot of the result. Let's see whether the Edublog Awards voting result will be different or not.

The MobileHost CoLearn system: mobile social software for collaborative learning

The paper "The MobileHost CoLearn system: mobile social software for collaborative learning" has been published in the International Journal of Mobile Learning and Organisation (IJMLO) by Inderscience Publishers. A preprint of this paper can be downloaded here.

Abstract:

Learning and knowledge are fundamentally social in nature – as emphasised by many researchers. In the past few years, there has been an increasing focus on social software applications as a result of the rapid development of Web 2.0 technologies. Furthermore, mobile and ubiquitous technologies have provided capabilities for more sophisticated open social systems, where mobile knowledge sharing is the norm. In this paper, we explore the use of Web 2.0 concepts and social software for learning and present the MobileHost CoLearn system; a mobile web services driven social software for mobile collaborative learning.

Reference:

Chatti, M.A., Srirama, S.N., Ivanova, I. and Jarke, M (2010) ‘The MobileHost CoLearn system: mobile social software for collaborative learning’, Int. J. Mobile Learning and Organisation, Vol. 4, No. 1, pp. 15–38.

PLEM: A Mashup-driven Long Tail Aggregator and Filter for Learning

I would like to share with you a new learning service called PLEM which can act as a mashup driven Long Tail aggregator and filter for learning.

PLEM as a Long Tail aggregator:

PLEM enables to collect a variety of niche learning elements (i.e. learning resources, learning services, learning experts, and learning communities) and make them available and easy to find. Everyone with an OpenID can log into PLEM and create a personalized space, where she can easily aggregate, manage, tag, rate, and share learning elements of interest.

Aggregation is supported by a federated search engine that enables to pull together learning resources from distributed sources, remix, and assemble them to form a new personalized learning resource collection (LRC). To achieve this, we utilize multiple social media search APIs to add open educational resources (via MIT OCW and OUNL OpenER), blogposts (via Google Blog Search and Technorati), videos (via Google Blog Search and YouTube), books (via Google Book Search), images (via Google Image Search and Flickr), and presentations (via Slideshare). The list of supported services will be extended to include e.g. other OER initiatives such as OUUK OpenLearn. The figure below shows the interface of this federated search engine. You can see here an example of an aggregated LRC.

The idea is not just to bookmark learning resources but to create a collection of the same, tag, rate, and share theses LRCs with others who can then save them to their spaces. The benefits of creating a LRC are twofold:

- Foster the concept of "The Learner as DJ". Scott Leslie and Harold Jarche talked about a similar concept: "The Open Educator as DJ".

- Finding a good LRC related to a topic we're interested in will be a huge time-saver. Recently, Firefox has adopted a similar approach with their new feature Add-on collections.

PLEM as a Long Tail Filter:

The primary aim of the PLEM filtering mechanism is to harness the collective intelligence to rank and recommend learning elements. The idea is quite simple, each filtering action on a learning element from the Web (e.g. comment, link, save, like, rate, vote, view, share) counts as one "vote" for that learning element. The mean value of all "votings" for a given learning element is then used to measure its popularity. As shown in the figure below, these "votes" currently include PLEM saves and ratings, Delicious saves, Friendfeed comments and likes, Yahoo inbound links, Digg votes, Google Trackbacks, and Technorati blog reactions. This list will be extended in the future to include other social media filtering services such as Twitter mentions and Diigo saves.

PLEF Requirements

I’m currently working on a Personal Learning Environment Framework (PLEF) that needs to address the following attributes:

- Personalized: PLEF should provide the learner with ability to incorporate a myriad of tools and services; and ability to determine and use the tools and services the way she deems fit to create her own PLE, adapted to her own situation and needs. It is crucial to provide access to a wide range of tools and services that support different learning activities such as production, distribution, reflection, and discussion. It is also important to enable customized search across the collection of learning items in one’s own PLE as well as in peer PLEs. PLEF should also offer learner-defined access control mechanisms for each PLE item, as well as support for multi-views of the PLE, enabling the learner to filter the mass of available knowledge sources based on her needs, and switch between multiple learning contexts.

- Social: PLEF should support the building of interactive environments by offering means to connect with other personal spaces, such that learners can engage in knowledge sharing and collaborative knowledge creation. Social features such as social tagging, commenting, and sharing have to be supported.

- Extensible: PLEF should have a flexible architecture enabling learners to enrich their PLEs with a heterogeneous set of services. A learner should be able to easily integrate, aggregate, and mash-up different learning services (e.g. feeds, widgets, media, lightweight JSON/REST-based Web Services) based on her needs and interests.

- Open: PLEF should be based on open standards (e.g. RSS, OpenID, OAuth, OpenSocial) to ensure interoperability and communication with other services. It should also provide a public API that can be used by third-party services.

- Ubiquitous: PLEF should provide means for flexible delivery and ubiquitous access to PLEs from multiple channels and wide variety of platforms and (mobile) devices.

- Filter: One concern with knowledge-pull approaches is information overload. Therefore, PLEF should provide powerful filters, that tap the wisdom of crowds (e.g. recommendations, ratings, rankings, reviews, votes, comments) to help learners find quality in the Long Tail.

- Easy to use: PLEF should provide rich experience with e.g. AJAX support. A learner should be able to copy-and-paste and drag-and-drop elements to personalize and manage her PLE with minimum effort.

What do you see are other critial requirements of a personal learning environment framework?

Google as a Long Tail Filter - Part 2

Having introduced the philosophies behind Google ranking in a previous post, Amit Singhal continues his explanation of how Google ranking works by giving an overview of the technologies behind their ranking system. Here are the points he stressed in his explanation:

- Understanding pages
- Understanding queries
- Understanding users

Google as a Long Tail Filter

A post by Amit Singhal introducing the core ranking team at Google. According to Amit, the philosophies behind Google ranking include:

1) Best locally relevant results served globally.
2) Keep it simple.
3) No manual intervention.

Digg Recommendation Engine

Digg released a recommendation engine in beta beginning this week as they write "to discover new content on Digg". More information about this new feature is available in the video below and in this Whitepaper.


Digg Recommendation Engine from Kevin Rose on Vimeo.