By Nic Newman Senior Researcher City University, London

Every day more and more content is created and distributed through social media, but the key problem for consumers and professional journalists alike is how to find the good bits.

The Social Sensor project is looking to find new ways of solving this filter problem. What algorithms can identify the best tweets, pictures or videos? How can we separate truth from lies in the heat of a fast moving news story?

Many of these issues were laid bare on election night (November 6th 2012) when in addition to traditional television and web coverage the drama of the night was also played out on Facebook and Twitter. We set out to monitor the range of conversations and identify the kind of information that could have been useful to professional journalists

The SocialSensor Infotainment use case has supported the 53rd Thessaloniki International Film Festival (TIFF) with its technologies. CERTH has released an update of the ThessFest, the official festival mobile application. The applications are available for free on iOS and Android.

ThessFest features the complete film schedule, as well as real-time updates from Twitter on what happens in the Festival. Specifically it offers the following features:

- Browse the updated Film Festival schedule by category and date.
- Search movies by keyword.
- See details of Festival movies and directors.
- Easily create and update your own screening schedule.
- Get directions on how to reach the Festival venues.
- Easily rate, tweet and comment movies.
- See real-time ratings, comments and tweets made by other users for each movie.
- Follow the Festival tweet stream.

SocialSensor has been actively pursuing standardization activities in order to recommend its findings and results to standardization bodies.

In this context, MPEG-7 contains a basic User Descriptor Scheme. However, this scheme is insufficiently expressive to represent the SocialSensor use-cases adequately. The consortium proposed an extension to the MPEG-7 standard to account for this discrepancy, which is currently under investigation.

SocialSensor successfully participated in the Social Event Detection task of the MediaEval 2012 workshop. MediaEval, a workshop focused on focused evaluation tasks with respect to multimedia analysis, took place in Pisa, Italy (4-5 October 2012). CERTH took part in the Social Event Detection (SED) task that involved three challenges: (a) detection of technical events in Germany, (b) soccer events in two major European cities, (c) detection of Indignados events in Madrid. All challenges were defined on a large set of over 160,000 images from Flickr. A more detailed definition of the task is available here.

In all the challenges, CERTH achieved median performance using a versatile and flexible approach developed within the SocialSensor project. The approach employed by CERTH is described here, while the presentation given at the workshop is available here. We have also made available the implementation of the approach in the form of a Java library.

The following SocialSensor deliverables are now available for download from the deliverables page:

  - D2.1 Entity mining and tracking in social streams
  - D3.1 Semantic middleware architecture and components
  - D4.1 Crawler for social and web resources
  - D4.2 Social indexing and search components
  - D5.1 User model and personalisation components
  - D8.1 Infotainment use case requirements & specs. v1
  - D9.2 Report on standardisation, dissemination and SUG activities v1
  - D9.3 Market analysis

SocialSensor has successfully contributed to the organization of this year's Social Event Detection task (SED 2012) that took place in Pisa 4-5 October, in the context of MediaEval 2012. The SED 2012 dataset has been made publicly available by CERTH for download and use by the research community. You can freely download the dataset from http://mklab.iti.gr/project/sed2012 . The downloadable archives include the following:

  - The three 2012 SED Challenges definitions,
  - The XML metadata for the images in the test dataset,
  - The actual image files of the test dataset,
  - Ground truth results for the defined challenges/dataset,
  - Our evaluation script.

Please feel free to use this dataset for research purposes, and also to disseminate the above information to anyone else who may be interested.