How to be aware of the trending and emerging topics everyone wants to read about?
What is Topic engagement?
Topic engagement is a service that shows what the leading topics from disparate sources of news articles for the day are according to the readers’ interactions with them. This way you can quickly decide whether to invest additional time and resources in a given topic.
How can Topic engagement help your business?
Gain a 360-degree view of information online and the customer interactions with it
Be up-to-date with the emerging topics in online and social media
Allocate resources and monitor your reputation online in a more optimal way
This technology has been adopted by a large publisher and helped them measure the overall media environment, audience engagement and the preferred topics of the day.
As a result, the client was able to improve their focus and optimise day-to-day work. We used a human-in-the-loop approach as we collaborated with domain experts to determine the machine learning algorithm input parameters for stop word lists, number of keywords, number of clusters and validating the relevance of the produced output. The result was the optimisation of the processes in the respective media group so that people working there could truly focus on what is really important and interests them. The tool allowed the journalists to understand at a glance what the hot topics of the day were.
The problem was that the journalists and editors had to analyse the content in other media every day, in order to be aware of what is happening in the world around them. We applied a topic engagement model to the selection of media (national and regional) which is monitored daily. The average number of documents per day was between 7K and 9K. We focused on the most relevant measurement indexes and based our conclusions mainly on them. For example, as decided together with the client in advance, we put less priority on factors that could be easily manipulated on purpose, such as Facebook comments.
Thanks to the technological models we described above, we grouped all these documents into thematic cubes, which contain not only the quantitative measures but also additional metadata which gives even greater insight into the individual topics. Thus, the time of journalists and editors who otherwise went into content analysis could be invested in the development of additional materials or other activities. This way, we provide a much more objective view of all the information that needs to be analysed. We gave our client the opportunity for a better and faster understanding of the developing topics in the media and measuring the amount of attention it was getting from the audience.