Category Archives: Emergent Semantics

Contribution @ I-KNOW 09 accepted!

The contribution of Christoph Kofler and me with the title “An exploratory study on the explicitness of user intentions in digital photo retrieval” has been accepted for publication and presentation at the I-Know ’09. Here is the abstract (the full paper will follow as soon as we have prepared the camera ready version):

Search queries are typically interpreted as specification of information need of a user. Typically the search query is either interpreted as is or based on the context of a user, being for instance a user profile, his/her previously undertaken searches or any other background information. The actual intent of the user – the goal s/he wants to achieve with information retrieval – is an important part of a user’s context. In this paper we present the results of an exploratory study on the interplay between the goals of users and their search behavior in multimedia retrieval.

This work has been supported by the SOMA project.


MEDICHI Notes: Complex Systems

Yesterday and today the MEDICHI Workshop on the Methodic and Didactic Challenges of the History of Informatics takes place here at the Klagenfurt University. Yesterday Michael S. Mahoney opened the workshop with a keynote talk about the history of software. The talk of Niklaus Wirth has been read by Ann Dünki, as Niklaus Wirth couldn’t come. Both talks were very interesting and recordings will be available on the Klagenfurt University Campus TV. However Ann Dünki said something very interesting: She tried to distinguish between complex and complicated systems:

Complex systems can be defined as systems that have emergent properties, which we observe but cannot understand easily.

My question: Social Software also has emergent structures and properties. So can we define social software as complex system?

CfP Knowledge Organisation & Semantic Technologies

This year’s Special Track on Knowledge Organization and Semantic Technologies 2007 (KOST ’07) will be a further cool event (well I’m a chair there, if that’s no guarantee 🙂 ). The special track will take place 5th September in Graz, Austria. Read the full CfP here.

Topics include but are not limited to:

  • Ontology engineering and knowledge representation
  • Ontologies in applied knowledge management
  • Ontology powered information systems
  • Information retrieval and knowledge organisation systems (KOS)
  • Knowledge discovery in the Semantic Web and on the Semantic Desktop
  • Modeling and retrieval of semantic metadata
  • Ontology learning and extraction
  • Emergent semantics & community knowledge in the web
  • Folksonomies as knowledge bases
  • Semantics in multimedia

Submissions are to be uploaded until 7th of April.

Tag Network Generation

sample-tag-network.pngYes I know … this is not about MPEG-7 and multimedia, but on the other hand its very interesting 🙂 Some months ago I started to analyze the structure and usefulness of folksonomies (see here or wikipedia). Especially I was interested in methods for tag similarity computation and the extraction of structure from the chaos of tags and resources. Today I finished an interesting little project, which allows me to create a tag network out of samples taken from The shown image (click to enlarge) shows a network generated from a list of popular tags from Dec. 28th 2007 in the afternoon. The color of the edges indicates the amount of similarity. Note that the used method does not result in a symmetric measure and therefore an undirected graph, but is normalized based on the source tag and is visualized as digraph.

The similarity of tags is based on the co-ocurrence analysis published by Peter Mika in Ontologies are us: A unified model of social networks and semantics. The visualization has been done with graphviz. The sample from has been taken by monitoring the RSS feed for recent additions.

Following Cow Paths

I’m here at the 2nd Symposium on Media Informatics in Bonn “Cow Paths: Agency in Social Software”. The main thing it is about is social software, but well … it has something to do with multimedia and metadata: According to Marc Smith, a sociologist from Microsoft Research, people leave traces (in bits and bytes) -> people start recording their lives in different aspects: sounds, images, videos, text, etc. Furthermore they generate a lot of patterns and metadata from their behavior. In a sense this allows more and more social studies … and it allows to infere semantics from different dimensions of user generated metadata. (see also their project netscan)
This process is discussed in length within the workshop on the symposium, which we (Armin Ulbrich and myself) are giving tomorrow … so stay tuned (we will post the slides on the portal associated to the event and give the link here to).