In the recent years, Natural Language Processing (NLP) has had a very fair amount of progress in spite of many challenges involved in it. The trend is expected to grow rapidly with further advancements in the coming years. Today, there is a plethora of diversified NLP solutions featuring new age technologies. As new solutions come along at a rapid pace, the need emerges for an objective method to compare their performance, scalability and cost. This vastly growing ecosystem makes it hard for people to compare features and performance of different systems.
In this post I have listed top 6 sentiment analysis solutions that are really awesome and I have worked with.
The Google Cloud Natural Language API provides natural language understanding technologies to developers, including sentiment analysis, entity analysis, and syntax analysis. This API is part of the larger Cloud Machine Learning API family.
This API returns a numeric score between 0 and 1. Scores close to 1 indicate positive sentiment and scores close to 0 indicate negative sentiment. Sentiment score is generated using classification techniques. The input features of the classifier include n-grams, features generated from part-of-speech tags and word embedding.
AlchemyLanguage is a collection of natural language processing APIs that help you understand sentiment, keywords, entities, high-level concepts and more. You can use AlchemyLanguage to understand how your social media followers feel about your products, to automatically classify the contents of a webpage, or to see what topics are trending in the news.
Stanford CoreNLP provides a set of human language technology tools. It can give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and syntactic dependencies, indicate which noun phrases refer to the same entities, indicate sentiment, extract particular or open-class relations between entity mentions, get the quotes people said, etc.
What if the film review covers several movies? Which movies were more positively received than others? Here, Rosette applies entity extraction to identify the movies and determines the sentiment for each one by relating the sentiment in the review to each entity. Our sentiment analysis provides entity-level analysis for 18 entity types out of the box, but can be retrained to extract and analyze custom entity types on-premise.
Lexalytics’ sentiment analysis tools can be configured to determine sentiment on a range of levels. They’ll score sentiment on a document level (does this express a general positive or negative tone), but they’ll also score the sentiment of individual words or phrases in the document. Lexalytics provides sentiment analysis solutions directly to businesses, as well as offering APIs for integration into our client’s own products.
The languages supported by the above mentioned products are given below.
|Google NL API||MS Linguistic/Text Analytics API||IBM AlchemyAPI||Stanford CoreNLP||Rosette Text Analytics||Lexalytics|
|Sentiment Analysis||English, Spanish, Japanese||English, Spanish, French, Portuguese||English, French, Italian, German, Portuguese, Russian and Spanish||English||English, Spanish, Japanese||English, Spanish, French, Japanese, Portuguese,