VEM: Video Opinion Mining

Video Opinion Mining(VEM) is a python module capable of extracting emotions from a video file based on it’s text(audio transcripted), audio or video, displaying the results in the form of a heatmap ploted in an arousal valence chart.

This project was developed focusing mostly in client satisfaction, but can also be used in other areas of emotion recognition.

If it’s your first time using the module, make sure to check the installation guide and documentation to make the experience easier.

There’s also an example code avalaible here https://colab.research.google.com/drive/1sYAYRxFdpa86Huxm-KVkEvQo6x8ZmgS6?authuser=1#scrollTo=yF78bgHtziJ6

This project was supported by the Ministry of Science, Technology and Innovations, with resources from Law no. 8,248, of October 23, 1991, within the scope of PPI-SOFTEX, coordinated by Softex and published Residência em TIC 13, DOU 01245.010222/2022-44 .

Thanks to Motorola and C4AI for financing and strengthening research within the AI ​​Center.

• Getting started
  • Installation
  • First steps

• VideoOpinionMining Documentation
  • EmotionMapGenerator
  • MultimodalOpinionExtractor
  • OpinionExtractionModel
  • OpinionExtractor
  • VEMProcessor
  • VideoSegmenter
  • get_labels()