1. The text analysis methodology behind Zurvey.io
1.1 Entity oriented sentiment analysis
Zurvey.io conducts automated sentiment analysis on every text unit. This means that the system automatically recognises phrases that have a sentiment value, and scores them between -3 and +3. The calculated phrase scores are summarized for the entire text, representing the sentiment of the response.
At the same time, the values for each recognised entity are also visualised for every text unit in our system. Those entities can be places, brands, organisations and even people of renown, resulting in a more layered understanding of the sentiments in the text.
1.2 Automatic topic recognition
Besides sentiments, the system automatically recognises key topics and entities in the texts: places, people, brands and organizations.
1.3 Available languages
Zurvey.io is available in Albanian, Bosnian, Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, French, Finnish, Georgian, German, Greek, Hungarian, Italian, Indonesian, Latvian, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swedish and Ukrainian. Our text analysis algorithm provides the same level of precision in each of these languages.