MixedEmotions = Big Linked Data Platform for Emotional Analysis
MixedEmotions develops innovative multilingual multi-modal Big Data analytics applications.
Our tools analyse a more complete emotional profile of user behavior using data from mixed input channels:
- multilingual text data sources
- A/V signal input (multilingual speech, audio, video)
- social media (social network, comments)
- and structured data.
Current components available for open source emotion extraction (Docker / Github):
|Audio Analysis||Estimating arousal, valence, age, gender, big 5 personality traits from audio
|Entity Extraction||Spanish entity extraction, NUIG||Docker|
|Topic Extraction||Spanish topic extraction||Docker|
|Orchestrator||The code of this orchestrator will let users have an starting point on how to interact with the platform modules.||Github|
|Sentiment Analysis||Java wrapper around several sentiment analysis tools, that was created for MixedEmotions project, created by BUT.||Github|
|Marathon||In this repository you will find Marathon configuration files for the different MixedEmotions modules that you can find in MixedEmotions’ Dockerhub.||Github|
|Topic Extraction||Topic extraction service||Github|
|Entity Extraction||Spanish entity extraction||Github|
|Scaner||Social Context Analysis and Emotion Recognition||Github|
|Audio Emotion Analysis||This module aims to extract emotions from audio, BUT||Github|
|Kibi||Kibi is a friendly – kept in sync – Kibana fork which add support for joins across indexes and external sources, tabbed navigation interface and more||Github|
|Senpy||A sentiment and emotion analysis server in Python||Github|
Commercial applications (implemented as pilot projects) will be in Social TV, Brand Reputation Management and Call Centre Operations. Making sense of accumulated user interaction from different data sources, modalities and languages is challenging and has not yet been explored in fullness in an industrial context.
Photo by Andrew Imanaka, image source flickr