+(91) 99007-25045
Sentiment Embeddings with Applications to Sentiment Analysis
  • Sentiment Embeddings with Applications to Sentiment Analysis

Sentiment Embeddings with Applications to Sentiment Analysis

Sold By Final year Student Project
Categories: , Tags: , , ,
  • Description
  • Reviews (0)

Product Description

Sentiment Embeddings with Applications to Sentiment Analysis

The proposed system provides a learning sentiment-specific word embedding dubbed sentiment embeddings. Existing word embedding learning algorithms ignores the sentiment of texts by considering only the contexts of words. This creates problem for sentiment analysis because the words with similar contexts but opposite sentiment polarity, such as good and bad, are mapped to neighboring word vectors.

The issue is addressed by encoding sentiment information of texts (e.g., sentences and words) together with contexts of words in sentiment embeddings. By combining context and sentiment level evidences, the nearest neighbors in sentiment embedding space are semantically similar and it favors words with the same sentiment polarity.

In order to learn sentiment embeddings effectively, we develop a number of neural networks with tailoring loss functions, and collect massive texts automatically with sentiment signals like emoticons as the training data. Sentiment embeddings can be naturally used as word features for a variety of sentiment analysis tasks without feature engineering. The sentiment embeddings to word-level sentiment analysis, sentence level sentiment classification, and building sentiment lexicons is applied.

Experimental results show that sentiment embeddings consistently outperform context-based embeddings on several benchmark data-sets of these tasks. This proposed system provides insights on the design of neural networks for learning task-specific word embeddings in other natural language processing tasks.


There are no reviews yet. Add a review