Gathering Information on this community as well as the current state-of-the-art in research and industry.
Venues of the community:
There are several events for the user modelling and adaptation community. However, both are closely related, which one can also see by the recent merge of two of the biggest venues UM and AH. I was told that besides the venues on international ground, ABIS is an important meeting on a national layer (The workshop has solely taken place in Germany, but gathers researchers across Europe).
- ABIS Workshop (Satellite event of the LWA Workshop)
- International Workshop on Semantic Media Adaptation and Personalization (2008)
- International Conference on Intelligent User Interfaces
- International ACM Conference on Recommender Systems
- Artificial Intelligence in Education (CfP 2009)
- User Modeling Inc. (check out more related conference, job postings, and research groups)
- Conference on Adaptive Hypermedia and Adaptive Web-Based Systems: All forms of Web and Hypermedia personalization from personalized search and browsing to recommender systems to personalized E-Learning. (2008)
- International Conference on User Modelling (2007)
- 1st and 7th International Conference on user modelling, adaptation, and personalization (2009): User Modeling (UM, 1986-2007) and Adaptive Hypermedia and Adaptive Web-Based Systems (AH, 2000-2008) have been merged into the annual conference series User Modeling, Adaptation, and Personalization (UMAP)
Professional Solution of Industry
- Amazon: Adaptive Hypermedia in eBusiness: Recommendations based on user preferences and prior history
- For further professional approaches see keynote by Alexandros Paramythis
Notes & Further Readings
- Adaptive Hypermedia (AH) tailors what the user sees to the learner’s goals, abilities, interests, knowledge, etc. [..] offers a selection of links or content most appropriate to the current user (in his current context, whereas context refers to the device). “Adaptive hypermedia is closely related to Web personalization.”
- Adaptive Educational Hypermedia: “Fundamental problem is that learners inevitably have diverse backgrounds, abilities and motivation – and hence highly individual learning requirements.” (AC 2005) Doesn’t target stand-alone systems (unlike intelligent tutoring systems), but hypermedia systems.
- Distinction between adaptation ((automatic) system-driven personalisation and modifications) and adaptability (user-driven personalisation and modifications).
- The Adaptive Web: Methods and Strategies of Web Personalization (Book by Peter Brusilovsky, 2007)
- AHA Project funded by the NLnet Foundation (1997 – up to date): see The Design of AHA
Towards adaptable and adaptive OMDoc (systems)
Looking at the work in the area of adaptive hypermedia, I believe, that ours and their work go well together: We have a strong representation format of mathematical knowledge (focusing on the design so far and slowly moving to ways of manipulating it, see e.g. JOMDoc/ JOBAD), while they have placed good thoughts on the user modelling, strategies for adaptation, and general frameworks for designing adaptive systems.
The motivation and focus of AH, seems to overlap with our work (cf. Peter Brusilovsky; AHA Project; Alexandra Cristea): For example, to improve accessibility of mathematical knowledge, we talk of adapting it, in particular by selecting, sequencing, and presenting mathematical knowledge for a user or community of users.
- Problems with hypermedia applications: (1) Navigational freedom: which links are relevant (for this user)?; (2) Comprehension: what has the user seen before when reaching a certain node? (3) Presentation: what fits the user’s screen? how much network bandwidth and processing power is available? (cf. Talk)
- Opportunities with AH: (1) Guide users towards relevant information (users can reach relevant information more easily and more quickly), (2) Make sure users can understand the presented information, (3) Change the presentation so that it fits the user’s platform and environment (cf. Talk)
Layers of the Adaptive Hypermedia Framework LAOS
If we look at the layers of the LAOS framework (cf. AC 2004), we can see a great overlap to the OMDoc approach. I believe we are much stronger on the content representation, while OMDoc is still missing the user modelling and adaptive layer:
- Domain model (DM) containing a collection of linked resources
- Goal and constraints model (GM) containing goal-related information, such as instructional and pedagogic information about the resources
- User model (UM) containing user-related information, such as information about the learner
- Adaptation model (AM) containing the behaviour and dynamics, such as, a learning style related adaptive strategy
- Presentation model (PM) containing display and machine-related information, such as the foreground-background colour scheme for the course presentation
In order to make OMDoc (systems) adaptable/ adaptive, we need to provide these layers: (1) OMDoc Commons interlinked on different layers, i.e. logical, narrative, rhetorical, argumentative (?); (2) theory morphisms, i.e. mathematical/ logical prerequisites but maybe also rhetorical prerequisites; (3) is missing; (4) is missing; (5) presentation-pipeline.