Microsoft yesterday announced the launch of a new Text Analytics service in the Azure ML Marketplace. In this initial release, Microsoft is offering APIs for sentiment analysis and key phrase extraction of English text.
Text Analytics API is a suite of text analytics services built with Azure Machine Learning. This initial release of the API can be used to analyze unstructured text for tasks such as sentiment analysis and key phrase extraction. We plan to add more capabilities to the API soon. No training data is needed to use this API, just bring your text data. We support English language only right now. This API uses advanced natural language processing techniques under the hood.
For sentiment analysis: the API returns a numeric score between 0 & 1. Scores close to 1 indicate positive sentiment, while scores close to 0 indicate negative sentiment. Sentiment score is generated using classification techniques. The input features to the classifier include n-grams, features generated from part-of-speech tags, and word embeddings. The classifier was trained in part using Sentiment140 data.
For key phrase extraction: the API returns a list of strings denoting the key talking points in the input text. We employ techniques from Microsoft Office’s sophisticated Natural Language Processing toolkit.
Read more about it here.