I must do sentiment analysis on a set of financial news from s&p500 for given entities (organization names), but the problem is that each news (rows in my dataset) may have more than one entity and I have to do analysis for each entity separately in a same news, first my algorithm should find which entities are present in a specific news and then do sentiment analysis for them. I would appreciate if someone could help me. example of output


A Ensemble of "Target based sentiment" models worked for a similar use-case that I worked on.

Some of the models that were part of the solution :

  1. http://sentic.net/sentic-lstm.pdf
  2. https://hal.archives-ouvertes.fr/hal-01537896/document
  3. https://arxiv.org/pdf/1802.05818.pdf

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.