Building a Deep Learning Model That Suggests Closest Emotions to Given Emotion

In this post, I will demonstrate how to build a model that, given an emotion and its effect/type (Positive Or Negative) get the three closest synonymous emotions to a given emotion.

I use an online dictionary sometimes, then I got a thought that why don’t I pick some synonyms for “hate” and “love” and build a Deep Learning(DL) model using Keras and Tensorflow backend, that uses Embeddings Vectors (To know more about Entity embeddings and advantages of them over OneHot encoded vectors click here). So below is the list of synonyms I picked from Dictionary.com

emotionsList= ['like','antipathy', 'hostility','love','warmth','loathe','abhor','intimacy','dislike','venom','affection',        'tenderness','animosity','attachment','infatuation','fondness','hate'] 

But to build any good model we need representative data, that’s when I thought I may need one more feature that helps my DL model to suggest better closest emotions. So I came up with “emoeffect” feature as below. For example, If someone says I like you, it gives a positive impression/feeling. But if someone says I hate you, it gives a negative feeling to us.

emoaffect= ['positive','negative', 'negative','positive','positive','negative','negative','positive','negative','negative','positive',               'positive','negative','positive','positive','positive','negative'] 

Here the objective is not to build the model with the best accuracy, but to generate best embeddings. So that we can use these embedding vectors to find closest matches. So we treat this problem as a  supervised task. The supervised task is just the method through which we train our network.

The complete code with explanation is available on Github at:

https://github.com/srichallla/DeepLearning/blob/master/DLmodelGetClosestEmotions.ipynb