Wednesday, January 17, 2007

A really bad idea of crowd-sourcing the Web

12,000 Estimated number of illegal immigrants apprehended at the U.S.-Mexico border in November

10 Number of illegals apprehended in November thanks to a $200,000 experimental website allowing anyone to monitor the border and alert authorities. Viewers sent 14,800 e-mails through the site.

Oh my god, what's gonna be next?? It's not enough that we can practice neighbour-watching in our own neighbourhood, but now, thanks to the Web, we are able to big brother our neighbouring countries, practice border patrolling, and renounce illegal immigrants. A little respé, svp!!,9171,1576859,00.html

Notes on Combining Social- and Information-based Approaches for Personalised Recommendation on Sequencing Learning Activities

This paper, Combining Social- and Information-based Approaches for Personalised Recommendation on Sequencing Learning Activities, cames from OUNL and is related to a bigger schema of works that those guys are carrying out on competencies. Thus, the context is very related to lifelong learning, namely to higher ed and vocational training.

The aim of the paper is to describe a domain model for "way finding". By the term "way finding" is meant "selecting and sequencing learning activities". The raison d'etre is:
Learners' problems in way finding will decrease the efficiency of education provision (the ration of output to input) and increase the cost. The local context for this paper is Dutch Open University student who lacks adequate information on study possibilities at an early stage of study, and problems in getting a good overview of the number and best sequence to study modules.

The paper describes a personalised recommender system (PRS) model that combines social-based (i.e. completion data from other learners) and information-based (i.e. metadata from learner profiles and learning activities) data to recommend the best next learning activity. The system is currently under development, a limited implementation is running using learner profile metadata.

Note about learning activities; OUNL has been very active in developing IMS Learning Design. They (Tattersall et al. (in press)) have previously proposed IMS-LD as a candidate to model learning paths. Moreover, they argues that its selection and sequencing constructs appear suitable for learning activities (units-of-learning) as well as for higher levels of granularity (e.g. competence development programmes). Interesting. At one point of time one could look how IMS-LD information could be generated in attention metadata (CAM).

So, the idea of PRS approach is a hybrid recommender that uses
  • a) information from other learners and their completion of tasks (completion is understood like rating) in a collaborative filtering manner (in text called social-based approach), and
  • b) information from students profile and c) metadata about the resource in the spirit of a content-based system (in text called information based approach).

Authors also argue that it is not enough to find the most efficient learning paths (like the shortest route in GPS), but to explore which paths are most attractive or suitable (like routes suited for biking), thus personalisation needed (individualised needs, interest, preferences or circumstances).

Other key concepts are:
  • learner's start position in a given domain (prior learning history)
  • aimed competence profile for that domain
  • learning path towards that competence
To develop a PRS the authors identify the following pieces, that the paper defines:
  • uniform and meaningful description of formal and informal learning paths
  • learning activities that are addressable and meaningfully described
  • uniform learner profiles that define needs and preferences
  • uniform competence description that defines proficiency levels
  • a learning path processing engine
  • an engine recording completion of activities
  • information matching techniques to enable personalised recommendation

Related work

I will later post on my blog some excerpts from my own literature review in the field of learning to show other recommender ideas based on the same hybrid approach, as in this paper they mention that this approach has hardly been applied in learning. There was only a reference to Herlocker et al. (2004).

In the related work section it is mentioned that education field imposes some specific demands for recommender. Main differences sited between recommenders for books are the degree of voluntariness (learning is many times required to obtain some goals) and the possibility to establish an explicit completion (as most learning activities are to be assessed for successful completion). Hmm..I do agree with the statement, but had come up with different reasons myself. Goes to show, I guess, how the initial requirements for a recommender system differ from what I'm working on.

An interesting outcome is cited from Janssen et al. (in press): learners were offered a recommendation "most successful learner continued with Y after having completed X". I call this an "Amazon-like" recommendation (other people interested in this book also bought x, y, z) based on clustering behaviour. There were no personal characteristics taken into account in this study. They found out that this type of recommendation enhanced effectiveness in completion of the set of learning activities, but did not increase efficiency, the time it took to complete them.

Authors also acknowledge the problem of insufficient data that can be derived from existing log files, the same that my colleagues are working on with the view on capturing attention metadata (CAM).


Authors state:
"From a self-organising point of view it would be ideal if way finding would emerge as a result of (in)direct interactions between members of the learning network, without being dependent of formalised descriptions in domain and user models."

I so agree: instead of investing time in describing all the information regarding the learner, his/hers existing and required competences; the resource; and the curriculum with goals and skills required, would be more interesting to tap onto existing knowledge from the masses and their previous experiences, the decisions they took to find the next suitable step, etc.

The authors also discuss the complimentary approach of controlled vocabularies or ontologies combined with annotations such as social tagging and rating, just in the same direction as we are doing in MELT (we talk about adding metadata a priori and a posterior) and what I'm interested in looking into.

Related to my work

The difference in what I'm looking into now and what this paper describes is, first of all, the context. I'm interested in a repository that is used mostly by K-12 teachers and learners (sometimes). The repository is not linked to formal learning requirements related to a curriculum, because it is used on the European level, where there are many curricula depending on a country or a local policy. However, each teacher who comes to that repository has his/hers own information seeking tasks, that I've talked about previously. Sometimes those tasks are related to covering a piece of a local curriculum, whereas some other times it is to find a piece of resource to support some generic learning goal, or find inspirational material, or something else.

Secondly, in my context of work sequencing learning resources is not the goal, rather just finding resources that fit to the search criteria and the task at hand. So I'm not so into this sequencing, however, I like the idea of playlists and using this type of expert knowledge of putting items together for learning purposes (the use of Case-based Reasoning like Claudio explore here).

Imagine if teachers could generate playlists of LOs as easily as I do playlists in iTunes (I'm NOT talking about automatically generating them, but hands-on deejaying). Then, those lists could be used as rules for generating new ones. In that case, we would not need LOM to know which item in a repository is described as "introductory item" or "motivational item" to start the lesson, or which one is good for "explaining a rule", but we could detect that information form playlists generated by teachers who knows through her domain knowledge that after this piece I put x,y and x. Let's see.

To check out from the paper:
- Koper (2005)
- Janssen et al. (in press) about the test
- Sicilia (2005) about ontologies to express competencies
- Van Setten, 2005 social-based approaches
- McCalla (2004), pragmatics-based paradigm of tagging learning activities with learner information

Wednesday, January 03, 2007

Fighting the read/write web-fatigue with interoperability

My problem with social software sites has long been my short attention span. I love to log-in - but not fully create my full profile as it is soo timeconsuming - I play around for some time to test and understand how some of the features work, and then I forget about it. Some random emails from even more random people wanting to make me their friend sometime remind me of the service. However, it's hard to go back as I can't even remember the password or which email I used to sign up.

This post, ..(cuz losing passwords is common amongst teens), really made me laugh about how teens use the Web. According to that teens would forget the password to enter to the social network service, and without any hesitation, they start a new profile, and email for that reason. I wonder if this is more the nature of teens than a new trend emerging among young users of Web?

Maybe teens just don't think the whole thing (i.e. social network sites) is that meaningful or worth saving. Or better, maybe they just really don't think about building a consistent profile of themselves, yet. Hell no, I would hate if all the stuff that I once did on the Web would be still available and indexed in Google! Everyone needs to start once in a while from scratch, cuz old habits stick (and stink)! But, maybe once those kids think that it's meaningful enough for them, and they will start remembering the passwords.

Or better, when they are old enough that they really care and want to keep all the digital pieces together, hopefully there are better ways to keep track of "yourself" than separate services with no portability of content that only rely on stupid passwords. There really should be better ways...

Anyway, the two points that I have seeing since I've opened my computer after vacations (yeah, I know how to log off) is Web-fatigue and portability of content, contacts and profile information in social networking sites, but I would really want to bring it to the whole field of social software.

Could 2007 be the year of social network fatigue? by ZDNet's Steve O'Hear --Another driving force for social networks in 07, will be the increasing
number of niche networks which are highly targeted to particular
interest groups or social activities. The question that still remains
however, is how many social networks any one user is likely to join and
remain active in? This is where Read/WriteWeb's prediction of fatigue
has more weight. Unless the time required to sign-in, post to, and
maintain profiles across each network is reduced, it will be impossible
for most users to participate in multiple sites for very long.
Therefore I think it will be essential for social networks to open up, through embracing open standards which allow for greater interoperability between networks.

Hell yeah, that would be lovely! That's what I've been wanting for some time now, well, ever since I started using social bookmarking services. I really like Furl, I think it's far nicer service to use than delicious, which I only use occasionally, because of peer-pressure, everyone else is there - well, to leverage on the crowds. But I just don't like it, for reasons that I won't go in this post.

Nevertheless, what I would like, is that having the profile and bookmarks that I've accumulated in Fulr could be taken advantage of also in delicious. There should be some way of updating my profile at the same time in both services, or that the services would have some way to make a personalised federated search across the services - sort of meta search across social bookmarking sites that would

a) allow me to browse other similar people's profiles,

b) would make active matching of my bookmarks to others in each service and recommend me links. Moreover, there should be some

c) possibility also to tap on my networks and contacts throughout the services, like that my delicious network would be notified of my new bookmarks in Furl.

Of course, now there are ways to do all that, subscribe manually users from one place to another, etc, but it would take ages to do it, and I would never be up-to-date in any of the places, I reckon.

So, this is to say that it would be really important to work on different types of interoperability between social software services. There's been posts regarding portability of contacts information, but also just plain user profile stuff (why can't I still even upload my vCard??), portability of social bookmarks (I once checked how about importing my personal links from delicious and furl to a repository of learning resources and found out that not even the RDF or XML was standard), etc.

The current way of wanting to lock-in people to a social software/service that they've started investing in (I'm thinking of investing time, knowing/inviting people and friends, creating and enriching profile, etc) is ridiculous. Only us, say, 30-years and +, are silly enough to stick around in places where we've started building up our personal portfolio of digital artefacts. We escape behind excuses like "I'm too busy to start a new blog and transfer my blogroll", or "I've lost my password to my domain name server to change it to a new one".. We should start seriously asking the providers for these services, to give us better portability of our data, do more open standards based communication layers to enable federated searches across services, etc.

Voila! My wish for 2007 is better interoperability for social software! Or otherwise, I'll just start behaving like those teens ;)