In this new information age, where information, thoughts and opinions are shared so proli cally through online social networks, tools that can make sense of the content of these networks are paramount. In order to make best use of this information, we need to be able to distinguish what is important and interesting, and how this relates to what is already known. Social web analysis is all about the users who are actively engaged and generate content. This content is dynamic, rapidly changing to re ect the societal and sentimental uctuations of the authors as well as the ever-changing use of language. While tools are available for information extraction from more formal text such as news reports, social media a ords particular challenges to knowledge acquisition, such as multilinguality not only across but within documents, varying quality of the text itself (e.g. poor grammar, spelling, capitalisation, use of colloquialisms etc), and greater heterogeneity of data. The analysis of non-textual multimedia information such as images and video o ers its own set of challenges, not least because of its sheer volume and diversity. The structuring of this information requires the normalization of this variability by e.g. the adoption of canonical forms for the representation of entities, and a certain amount of linguistic categorization of their alternative forms.
This calls for a range of speci c strategies and techniques to consolidate, enrich, disambiguate and interlink extracted data. This in particular bene ts from taking advantage of existing knowledge, such as Linked Open Data, to compensate for and remedy degraded information. A range of techniques are exploited in this area, for instance, the use of linguistic and similarity-based clustering techniques or the exploitation of reference datasets. Both domain-speci c and cross-domain datasets such as DBpedia or Freebase can be used to enrich, interlink and disambiguate data. However, case- and content-speci c evaluations of quality and performance of such approaches are missing, hindering the wider deployment. This is of particular concern, since data consolidation techniques involve a range of partially disparate scienti c topics (e.g. graph analysis, data mining and interlinking, clustering, machine learning), but need to be applied as part of coherent work ows to deliver satisfactory results.
The KECSM 2012 workshop aims to gather innovative approaches for knowledge extraction and consolidation from unstructured social media, in particular from degraded user-generated content (text, images, video) such as tweets, blog posts, forums and user-generated visual media. KECSM has gathered novel works from the elds of data analysis and knowledge extraction, and data enrichment, interlinking and consolidation. Equally, consideration has been given to the application perspective, such as the innovative use of extracted knowledge to navigate, explore or visualise previously unstructured and disparate Web content.
KECSM 2012 had a number of high-quality submissions. From these, the 8 best papers were chosen for the two paper sessions of the programme. To initiate the workshop, a keynote on perspectives of social media mining from an industry viewpoint was given by Seth Grimes.
We sincerely thank the many people who helped make KECSM 2012 such a success: the Program Committee, the paper contributors, and all the participants present at the workshop. In addition, we would like to add a special note of appreciation for our keynote speaker, Seth Grimes, and the ARCOMEM project (http://www.arcomem.eu) for funding the best paper prize.
The best paper award was kindly sponsored by the European project ARCOMEM (http://arcomem.eu).