Analyzing sport news - an integrated solution

Article illustration - Text analysys stories

PROBLEM

Tranzpress, the international language & media intelligence company--providing full-scale localisation services from translation to dtp, from software localisation to testing in over 40 language pairs--needed a solution to analyze its collected sports news from 2016-2017 in Hungarian and English.

It was important to perform human-level precise sentiment analysis on their news database. They needed to make difference between very positive, positive, neutral, negative and very negative mentions.

As there were some key sport events it was important to analyze only the opinion that are directly targeting these events in the news on both language and to not analyze the related sports results just the event opinion and experience. Reviews and more personal summaries of events were collected mainly.

Here is an English example: https://bit.ly/26900Pj This is a Hungarian example: https://bit.ly/2TAA660

SOLUTION

They decided to choose Neticle Text Analysis API as the perfect solution to their needs. They integrated both document and entity-level sentiment analysis for the news.

Neticle's methodology for quantifying opinion phrases fitted well to this purpose. The 7-point scale from -3 to +3 covers 3 stages of tone intensity in each polarity direction: very negative, negative, slightly negative, neutral, slightly positive, positive, very positive.

They converted Neticle's sentiment score to the sentiment categories needed:

  • positive: 1, 2
  • very positive: 3
  • neutral: 0
  • negative: -1, -2
  • very negative: -3

Here are some illustrative charts from the output analysis, showing the ratio of positive, negative and neutral mentions, reach numbers and key authors of sports articles:

Text Analysis Story#1 illustration Text Analysis Story#1 illustration Text Analysis Story#1 illustration

They defined keywords to cover the event and also analyzed the key locations (cities) in the news to understand the perceptions of the organizers cities.

They defined keywords to cover the event and also analyzed the key locations (cities) in the news to understand the perceptions of the organizers cities.

We needed 1 week to integrate Neticle text analysis and 8 hours for net development tasks and finetuning.

OUTCOME

Tranzpress has have been using the integrated solution for 3 years and no extra work needed to be done. News are analyzed real-time with human-level precision and showed on their dashboard.

As for future steps in our cooperation, we plan to involve further newsfeeds in their system.

Do you have a story, article or research about branding and social listening? Be our guest writer! How? Just download our guide here, write us and we'll publish your article.