Sports is a topic with many voices, opinions and commentary. Information is plentiful but objective, descriptive, real-time information is hard to find in an opinionated world. With social media in particular, it’s hard to separate fact from opinion and follow what is actually happening. The ability to find objective, descriptive, real-time information is not as easy as it should be.
Objective sports data
neuspo is laser-focused on identifying fact-driven, real-time event data from sports social media and news data. The platform looks to set an example of media providing tailored experiences to distinct topics of interest, with clarity into how content is recommended.
neuspo strives to provide the following:
- Discovery of interesting sport events
- High quality in-game play-by-play data
- Objective team updates
- Insights and game predictions
Sport events are typically defined as a game, two teams playing against each other. But events can also be a trade, free agent signing or a coaching change. With these events will come a mountain of commentary on why it was a good or bad move, sometimes clouding what the actual event was.
Play-by-play data shows the event flow of a game. Goals, touchdowns, home runs, baskets, impactful defensive plays all will show throughout play-by-play data.
In both cases above, neuspo summarizes an event stream to bubble up the most relevant information.
Sports is also increasingly analytical in its own right. Analytics play a large part in the decision-making process of building a successful team. neuspo will have authored content that discusses relevant, fact-driven sports insights.
neuspo uses the Twitter Streaming API to access real-time social media data. Objective and descriptive messages are identified in real-time, from the incoming stream of messages. Events are discovered based on trending topics.
The image above describes two different events that were discovered from the event stream. Each event represents a game or an important team update. To the left of the event is an excitement index. The excitement index is a measure of the interest in a particular event. For a game, it also shows a breakdown of interest per team. More circles and squares mean more interest.
Message streams are analyzed once grouped into topics and the most relevant and impactful messages are nominated for use. From the nominated messages, a summary is generated. neuspo works to build the most concise, objective and descriptive message at a given point in time.
Message summaries frequently change during high traffic times, when games are occurring. The latest, most relevant and recent events are shown at the top of the screen.
What is objective vs subjective? How do you tune out unrelated content?
With recent advances in data science and machine learning a number of methodologies can be used. For neuspo, machine learning models were tuned to find relevant sports content. Additional models are also used to judge if statements are objective or subjective, along with the reliability of the author. There is a balancing act in being too objective where it’s not descriptive and sounds robotic. Excitement isn’t necessarily subjective.
neuspo is an example of having content recommendation algorithms tailored to a specific audience. Having insight into how content is prioritized and displayed is beneficial. Users can self-subscribe to different communities and customized experiences can be built that add value to a given audience.
The concepts behind neuspo can be applied to different domains or even the same domain with a different objective. An example being, if you only wanted subjective team commentary.
See it in action
neuspo is a start towards delivering a different way of viewing media content. The machine learning algorithms used are just the beginning of what is possible. There are also a number of insightful discussions that can be fostered from analysis of the data.
Try the app @ https://neuspo.com