The news use case targets two end user groups: (a) news professionals (journalists, editors, analysts) that are interested in leveraging UGC in their work, (b) casual online and mobile news readers. With respect to professional usage, different scenarios will be supported, such as discovery of emerging trends and topics, aggregation of UGC with professional content, analysis of massive amounts of social data for new insights and profiling of news portal users and recommendation of relevant content. 

The SocialSensor News prototype identifies key influencers in social networks who are active in sharing news or have demonstrated expertise in a particular field of interest. Information and data from these "news hounds" ensure that topics, trends and trust scores are useful for professional and general news users alike. Interfaces have been developed for web, mobile and tablet.

A SocialSensor News prototype has been developed which combines the discovery of topics with the aggregation of content from multiple networks: Experienced journalists from several media organisations as well as digital experts have successfully evaluated SocialSensor and confirmed the scientific and conceptual approach. Unlike other applications, the project's technology and interface focuses on the needs of modern multimedia newsrooms.

A mobile prototype (app) was also produced for an iPhone, which mirrored the key user journey journeys and added a few mobile specific features such as surfacing social media 'nearby'.

Casual news readers wil benefit from innovative new features, such as real-time discovery of news items, personalised to the user, proactive delivery (push) of relevant content to user based on their context, and socialisation of user with other news reader through ad hoc social networking. A new user interface has been designed for casual news readers, whose initial concept is shown in the figure below:

In general the response of evaluations' participants was positive. The application was considered useful, significantly different from other tools on the market and worth using every day, pending the modifications that the participants suggested. The following graph shows feedback on the overall experience, specifically about the ease of use of the whole interface, the organization of the content, the responsiveness of the interface, the advantage of the tools over Twitter (in terms of new content discovery or for general news browsing) and news portals, and the will of using the application on a day-by-day basis.

During the final year of the project, the SocialSensor team will focus on:

• Refining the news trends algorithm
• Identifying key influencers in social networks and improving individual trust scores
• Elaborating the SocialSensor mobile application.

The SocialSensor User Group (SUG) is a community of relevant stakeholders from the Social Web (beyond the project consortium) including mobile application developers, researchers, news organizations, event organizers, social networks, advertisers and other relevant companies and users. SUG members will be informed about the latest SocialSensor progress and developments and after specific agreements it will be possible to participate in the evaluation of the project results, test the project software platforms and provide feedback. It will be possible to establish synergies for the possible exploitation of the project results, the development of business models, partnerships and participate in the technical discussions and activities (special sessions, standardization, etc) and contribute with ideas or requirements that may fit the project objectives.

Current members list of the SocialSensor User Group:

Dr. Yiannis Kompatsiaris

e-mail: ikom@iti.gr
tel: +30 2311 257774
fax: +30 2310 474128

Centre for Research & Technology - Hellas
Information Technologies Institute
6th km Charilaou - Thermi, 57001, Thessaloniki
P.O.Box: 60361
Greece

SocialSensor collects, processes, and aggregates big streams of social media data and multimedia to discover trends, events, influencers, and interesting media content.

Watch this video to learn more about SocialSensor

Twitter, Facebook, YouTube, Instagram, and other social media platforms, all produce an overwhelming amount of data. Whether they use social media casually or professionally, users are finding it increasingly difficult to stay on top of what’s happening across the range of available platforms.

The aim of the SocialSensor project is to develop software that meets this challenge. The result is a set of software applications that collect data from social media and automatically transforms it into interesting, relevant, and entertaining content for the purposes of both news and infotainment.

The vision that has guided the SocialSensor project can be summed up in a single sentence: “SocialSensor quickly surfaces trusted and relevant material from social media - with context.”

·       quickly:  SocialSensor works in real time;

·       surfaces:  SocialSensor automatically discovers, clusters, and searches;

·       trusted: SocialSensor automatically supports the verification process;

·       relevant: SocialSensor personalizes content;

·       material:  SocialSensor handles text, images, audio and video;

·       social media: SocialSensor utilizes a number of social media platforms;

·       with context: SocialSensor organizes content by location, time, sentiment and influence.

News and Infotainment

SocialSensor is for anyone who wants to know what’s happening on social media. In particular, the SocialSensor project has been guided by two ‘use cases’: news and infotainment.

- ‘Professional news’ and ‘casual reader’ applications.

-  For use by professional news editors, journalists, and casual readers. 

 - To discover new interesting social content and integrate it in the news creation and    
   delivery lifecycle.

- EventLive’, ‘Dashboard’ and ‘Social Media Walls’ applications.

- For use by everyone. 

- To use new multimedia search tools and unique media consumption experiences whilst     attending large events, such as music festivals.

Results of the work done with respect to these two use cases can be found in the results as well as the evaluation sections.

How SocialSensor works

The SocialSensor project has developed a new framework for enabling real-time multimedia indexing and search in the Social Web. SocialSensor has moved beyond conventional text-based indexing and retrieval models by mining and aggregating user inputs and content over multiple social networking sites. Social Indexing incorporates information about the structure and activity of the users’ social network directly into the multimedia analysis and search process.

To do this, the SocialSensor project has developed and introduced the concept of Dynamic Social COntainers (DySCOs), a new layer of online multimedia content organisation with particular emphasis on the real-time, social and contextual nature of content and information consumption. Through the proposed DySCOs-centered media search, SocialSensor integrates social content mining, search and intelligent presentation in a personalized, context and network-aware way, based on aggregation and indexing of both UGC and multimedia Web content.

Several of the project key components are available as open-source projects on GitHub.

Get SocialSensor

SocialSensor for mobile

A beta version of the SocialSensor ‘News’ iPhone/iPad mobile app is available now from the iTunes Store.

Other software applications that have been produced during the course of the project can be found in the applications section.