Archive for the ‘LWA 2008’ Category

User modeling and Adaptation

Thursday, October 23rd, 2008

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).

Subscribe to more news: Mailinglist by TUE

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

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:

  1. Domain model (DM) containing a collection of linked resources
  2. Goal and constraints model (GM) containing goal-related information, such as instructional and pedagogic information about the resources
  3. User model (UM) containing user-related information, such as information about the learner
  4. Adaptation model (AM) containing the behaviour and dynamics, such as, a learning style related adaptive strategy
  5. 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.

Flexible, Automous Behavioral Control

Wednesday, October 8th, 2008

Flexible, autonome Verhaltenskontrolle: Erlernen und Adaptation von Sensormotorischen Raumrepräsentationen
Keynote by Martin Butz (COBOSLAB, University of Würzburg) at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: FGWM

On the Evaluation of Personal Knowledge Management Solutions

Wednesday, October 8th, 2008

Evaluating Tools of the X-COSIM Semantic Desktop
Presentation by Thomas Franz at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: FGWM

Hypothesis: PIM benefits from information linkage and information reuse across PIM application.
Method: Using RDF and Semantic Web technologies.

X-COSIM provides the X-COSIMO ontology:
Among others, X-COSIMO defines contextual information in a formal representation for context, the contextual ontology includes concepts such as email, attachment, sender, recipients. Attachments e.g. contextualizes information object, while sender and recipient contextualizes agents in the systems.

Evaluation:
Does an X-COSIM enabled desktop provide better support for PIM tasks than a conventional one?
Better means: increased effectiveness (absolute time spend on each task), increased efficiency (goals reached: distance of mouse movements, number of window switches, …), increased satisfaction (questionnaire, ratings, interview).

  • 18 participants: 3 graduate students and 15 Ph.D.s students; none of them used the semantic desktop before.
  • Introduction (to the scenario, to the dataset, get acquainted to the system), observation, and feedback phase.
  • Scenario: Real data select from the organizers of the Night of Computer Science in Koblenz (more than 140 emails, 44 files, 40 files via eMail, …)
  • Tasks: (1) organization tasks (familiarization: all emails in one folder and participants had to create a folder structure), (2) lookup tasks (baseline: re-finding information; baseline as this feature was not expected to be of greater benefit in contrast to others), (3) multi-item tasks (evaluation), (4) document-driven collaboration (evaluation), (5) information collation (evaluation)
  • Evaluation Wizard: guiding the user through the evaluation; presenting the lookup tasks, …, and questionnaire. The wizard tracked the execution time for each task.

Results: Semantic desktop can improve PIM.

Implementation: Runs on KDE with Thunderbird. download now

The Anti-Social Tagger – Detecting Spam in Social Bookmarking Systems

Wednesday, October 8th, 2008

Presentation by Andreas Hotho at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: KDML

The social bookmarking system BibSonomy has to deal with a lot of spam; which hamper the quality of search results and navigation. This talk focuses on detecting users as spammer, making all their posts invisible in the system. This decision is based on their tagging and personal data such as eMail etc. The authors present a framework that allows for automatic classification of spammers.

How to detect Spammers: Checking all their tags and, possible, the bookmarked sites. Spam posts are identified if:

  • Tags describing a web page do not fit to the content of the site.
  • Tags and/or topic of a post are not interesting for the system.

Problems:

  • Subjective notion of what is spam
  • No cross-check; noise
  • Only two classes: spam or non-spam
  • Maybe identification of spammers to not granular enough, rather flag posts as spam
  • User may have several accounts

Features:

  • Profile features (digits in name, digits in mails, length of the names, mails)
  • Activity features (time between registration and first post, number of tags per post – spammers use more, …)
  • Location features (number of users in the same domain or IP address)
  • Semantic features (automatic tag from spamming software “$Group” can be used to make tags public in some bookmarking systems, blacklist of spam tags, co-occurrence of information as “a spammer shares resources with about 18 other spammers, but only with 0.5 non-spammers”)

Classification algorithms: SVM (best), J48, Logistic regression (worse), and Naive Bayes

Capturing the needs of amateur web designers by means of examples

Wednesday, October 8th, 2008

Presentation by Victor de Boer (Human-Computer Studies Laboratory; University of Amsterdam) at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: ABIS

The authors present a tool (SiteGuide) that supports amateur web-users to design web pages: Helping them to select and organize information for their pages. User input a set of example sites that are similar to their intended website. SiteGuide scrapes and analyses the sites and captures their commonalities in a web site model. From this, SiteGuide generates a site for the users. In addition, the system can provide the difference of a draft site of the user to its internal model of the example sites.

Computational Intelligence for Communication and Cooperation Guidance in Adaptive eLearning Systems

Tuesday, October 7th, 2008

Presentation by Mirjam Köck at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: ABIS

Motivation: eLearning has become very popular, but still simple approaches of implementing adaptivity dominate. Computational intelligence is under-represented. The authors focus on challenges such as the autonomous knowledge acquisition, autonomous pattern identification at run-time, and expression of patterns in rules.

Adaptive learning guidance includes

  • navigation through learning materials
  • Guiding communication and cooperation activities (suggestion communication partners, contact persons for questions, …)

Approach: Using communication and collaboration activities (rather than contents/ tags) are used as input for the user models. Identify groups of learners based on communication and learning behaviours (observing the style of learning, the level of activities, activity pattern).

Collecting information such as the user’s online time, actions related to communication (read, write, update, delete), user’s current knowledge, learning activities (time needed for test, time spent on content before taking tests, performance of tests), content of communication items

Relations of interest: How is a user’s time spent on communication related to the learning curriculum?; does the knowledge state influence communication?; what is the degree of similarity between a user’s activity level in the communication area and content area?; …

Promising Technologies: Artificial Neural Networks (can discover activity clusters, can adapt components e.g. change weights, do not depend on continuous human intervention; but: blackbox-syndrome, missing explanation capability, rule extraction is difficult); Combined Neuro-Fuzzy Approaches, Bayesian Networks (combination of domain knowledge and data; derivation of causal relationships) -> Combination allows using Neural Networks e.g. for learning and making the hidden sector of Neural Networks more visible.

Prospect: Improve adaptation; reducing human efforts to ensure quality and up-to-dateness of model data; semi-automatic pattern recognition, classification and evaluation at run-time; predication of behaviour based on correlations; integration of CI approaches into popular learning environment (Sakai; see also Stephan Weibelzahl)

Towards an Automatic Service Composition for Generation of User-Sensitive Mashups

Tuesday, October 7th, 2008

Presentation by Thomas Fischer (University of Jena) at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: ABIS.

Mashups extract and combine data, functionalities, etc. from different websites into a single integrated tool.

See also Why Mashups = (REST + ‘Traditional SOA’) * Web 2.0

Evaluating the Usability of Adaptive Recommendations

Tuesday, October 7th, 2008

Presentation by Stephan Weibelzahl (National College of Irland) at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: ABIS.

Stephan Weibelzahl developed HTML-Tutor, an interactive learning environment which offers an introduction to HTML and publishing on the Web.

Most system in academia remain at the prototype level with poor usability. This is acceptable as prototypes are vehicles to provide proof of concepts of an approach. However, in the long run scientists need to demonstrate the effects and impact of adaptive systems. Consequently, we need to start taking usability criteria into account when developing and evaluating scientific software. The authors aim at analysing the effects of usability on adaptation.

An adaptive peer finder is presented. The system is based on the adaptive learning system AHA! by de Bra and Calvi.

Further Readings:

Adaptive Treemap Based Navigation Through Web Portals

Tuesday, October 7th, 2008

Presentation by Sirko Schindler (University of Jena) at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: ABIS (collaboration with Andreas Nauerz). (see paper)

Treemaps were proposed by Johnson & Schneiderman in 1991. The author propose adaptive treemaps – displaying different treemaps to different users – to improve the navigation in web portals. To test several algorithms, the author developed a prototype, which is embedded into the IBM WebSphere Portal.

Making Legacy LMS adaptable using Policy and Policy templates

Tuesday, October 7th, 2008

Presentation by Arne Koesling at Lernen, Wissen, Adaptivität (LWA 2008), University of Würzburg, 6.-8. October 2008. Track: ABIS

Focus: Introduce Adaptability into regular Learning Management Systems (LMS) – introduce sophisticated rule systems (policies) that allow all stakeholders (learners , teachers, system admins) to adapt the system for their needs.

Policies are statements that define the behaviour of the system and are intended to guide decisions and actions. There are also known as business rules. For example: “New customers have to pay in advance, regular customers are allowed to pay after delivery” or “point all users to the basic material, if they enter the course the first time and notify all tutors”. Policies are dynamic, declarative, reusable, have a well-defined semantics, and allow for reasoning.

The author chose Protune as policy language, which additionally supports negotiations, explanations and integration with external sources (see concrete examples in Protune on the w3.org website).