By the end of June, we took part in the TVX 2014 international conference on interactive experiences for television and online video with a demo entitled “Numbat – Tracking Buzz and Sentiment for Second Screens”. On it we showed our work and expertise on social media analytics applied to television and live events, combining semantic analysis technologies and real-time data processing to get metrics on social audience and opinions about each feature of the live program or event.
Social TV is not only a continuously growing area, but also a thoroughly mature one, with dozens of companies interested in user interaction and social marketing. Social media are giving particular importance to this interaction between users and TV broadcasts. To realize how far the social conversation about international events goes, you could take a look at Twitter’s recap on FIFA World Cup 2014 group stage.
During the conference we could see the ways industry and researchers are taking to make their point on Social and Interactive TV. For example, second screen applications allow viewers to have a deeper understanding on what they are watching, providing additional information related to the broadcast (usually ad hoc and synchronized for a better user experience) or through automatic trends discovery. Other approaches try to help users finding the right TV programs by studying their habits and behaviors when watching television.
Numbat is a tool that allows viewers to get a quick visual about the overall buzz and the audience’s opinion on each character or key topic about a live event. It uses MeaningCloud APIs, combining sentiment analysis technology with entity recognition and topic extraction.
At this point, we have to face the problem of browsing and searching over the captured information. Our tool offers a simple navigation interface based upon characters, topics and time within the broadcast. Based on Elasticsearch, a search engine built on top of Apache Lucene, and its faceted search and aggregation capabilities, Numbat is able to organize the social conversation for an easy browsing, generating at the same time audience metrics and buzz charts (per minute) on a specific topic.
Using Twitter’s streaming APIs the tool analyzes each comment’s text, and by extracting and recognizing entities, it distinguishes the events and the characters they are talking about. This allows the viewer to obtain a general overview of the buzz each topic generates, as well as trending topics on each program and character, updated in real time and synchronized with the action on TV.
You can see a similar visualization of this concept in the new Twitter Reverb tool.
We are getting used to see this kind of visualizations on TV, as typing about live events in social media is getting trendy, and TVs are showing these comments on screen (with more or less real-time capabilities). But this kind of approach is based only on simple mentions of words or users. Numbat, making use of semantic analysis technology and automatic dictionary creation (in the management layer), is able not only to count mentions, but also detect polarity about the opinions of all these comments.
In addition, this tool is being developed with an eye on being able to embed each of these visualizations separately on webpages, second screen applications, video walls, etc. Because of this, it offers a great flexibility, both in terms of the platform and the type of the event to monitor. It could be a TV program or show, but also a concert, a conference, political elections…
If you are interested in Numbat, you can read a presentation about the TVX 2014 demo below.