User Models for Adaptive Hypermedia and Adaptive Educational Systems

I don’t know if any one has done this before, but it would be a brilliant idea to combine Adaptive Educational System with Adaptive Information Recommenders in the form of a giant Adaptive Educational Recommender System including every possible type of know-how. By which, we could have the ability to provide personalized access to educational resources while generating recommendation learning knowledge or procedure to users either by the system or from other users.

In the mean time, I believe knowledge sharing is the most amazing job in the world for the glory prospects of all human being personally, so maybe we could even encourage users to devise his own learning materials or methods and share them with friends or communities.

Some one may doubt how we can believe the contents of the knowledge users posted. That’s a good question, however, for the authentic reliability of user-created learning materials, we could introduce the way in which Wikipedia works, which utilize the voting from users to preliminary delete and let the administrator, make the final decision of deletion.

Some one may criticize the system would be a mess when users try to find his own cup of tea especially facing the abundance of information available in the system, which raised another two problems, but for this one, I think it’s always the challenge of recommendation algorithm designing to make user exploring more quickly. Let’s face it and do a better job in user profile modeling. The second problem due to the abundance is that how to keep learning process structured and well formed, since that’s the way how we learn knowledge in depth. Because we learn every day, most of our knowledge was not from blackboard and knowledge was even better learned outside the class. But before I doubt if there is other approach that also works, I need to do research on cognitive learning process. Let’s hold this question. The third problem is that different from blackboard styles learning where students are kept concentrated on current topic till the goal is achieved, we have too much information in the system which may be a distraction to the focus required learning process. In my opinion, other than creating better interface to facilitate the learning process, we could introduce passive learning and positive learning based on the user’s personality by encouraging users either from the system or from the user.

This is a cool system only if we have large amount of users and user activities, but worth to try out.

Modeling user profile by tracking social networking activities

First of all, I apologized and I truly respect the privacy issue rising from the term “tracking”, but that’s actually how I started thinking about this topic.

Different from group profile modeling, we can model the communication among the social networking. Like there is a saying, “to know a person, better to know person close to him”, if you wanted to know someone well, it’s better to get to know friends close to him and to see how he interacts with them while you directly interact with him. For example, Joey posted his new Air Jordan shoes on facebook, and Mike later liked it some much by clicking like on this post. If we could model this activity as an interest of Mike, we surely would recommend this type of shoes to Mike in case we are doing online commerce recommendation.  Maybe this example sounds like naïve, however it conveys a new approach for modeling user profile, in my opinion. As the development of social networking grows exponentially, actually I could not have a picture in mind of how individual’s life is going to be changed, but one thing will happen for sure is that people are more and more connected to each other. Given by the huge amount of communicational information among them, the current technology has paved the way of new user profile modeling and let's see.

When I came up this idea, I did a little bit research into this area. Interestingly, IBM actually had already started this research about in 2011, in the paper “Unified Modeling of User Activities on Social Networking Sites” by IBM research, the author attempted at the unified modeling of various such activities on social networking sites to predict user’s future post, followship and friendship. This paper relates to my opinion on the same motivation of using huge amount of communicational information available for user modeling.