Senpy: A framework for semantic sentiment and emotion analysis services
作者:
Highlights:
•
摘要
Senpy is a framework to develop, evaluate and publish web services for sentiment and emotion analysis in text. The framework is aimed towards both developers and users. For developers, it is a means to evaluate their classifiers and easily publish them as web services. For users, it is a way to consume sentiment analysis from different providers through the same interface. This is achieved through a combination of an API aligned with the NLP Interchange Format (NIF) service specification, the use of semantic formats and a series of well established vocabularies. The framework is Open Source, and has been used extensively in several projects. As a result, several Senpy Open Source services are available for use and download.
论文关键词:Sentiment analysis,Emotion analysis,Linked data,Classification,Evaluation
论文评审过程:Received 10 April 2019, Revised 2 September 2019, Accepted 3 November 2019, Available online 7 November 2019, Version of Record 7 February 2020.
论文官网地址:https://doi.org/10.1016/j.knosys.2019.105193