Using Natural Language Processing (Nlp) And Deep Learning To Analyze Sentiment In Memes
Social media is the most popular interactive platform which is most common among people, today memes are a hot topic. Originally memes originated to have funny content but due to later development, it rather can be offensive sometimes, usually some hateful message or character image. Some memes may have abusive content and have the wrong impact on our society. It‘s difficult to categorize such memes with Human interaction This paper presents an approach to analyze and detect sentiment in memes using Natural Language Processing (NLP) and Deep Learning. It will detect offensive memes, in three steps. First, it will extract the text from the given image, then it will classify the given text as offensive or not offensive. If the text is found to be offensive then in the third step it will further classify offensive text in three categories namely slight offensive, very offensive, and hateful offensive. The model uses very simple architecture with a multi-layer dense network structure involving NLP with RNN and LSTM along with word embeddings such as GloVe and fast text.