CSAT: Citation Sentiment Analysis ToolFirst Prize in AirTech 2016 - Project Exhibition and Competition
|Area: Semantic Web, NLP, Sentiment Analysis|
|Supervisor: Imran Ihsan|
|Team: Osama Ahmed Tahir, Ali Jasim Bukhari, Waleed Khalid|
|For: Air University, Islamabad|
|Tools & Technologies||Microsoft .NET Framework,
Stanford Core NLP,
|An Ontology based sentiment analysis using Natural Language Processing and Computational Linguistics on Scholarly Big Data.|
|A scientific paper contains valuable information about scholarly activity and its evolution. A citation has the potential to reveal important and interesting information about a particular scholarly research. Most of the techniques available today on citation analysis are somewhat based on the principal of number of citations. Citation Content Analysis (CCA) is a technique to analyze citation meaning from the nature of academic writing itself. Citation Sentiment Analysis aims to determine the sentiment polarity that the citation context carries towards the cited paper. The categories of sentiment polarity could be either positive, negative or neutral.
CSAT is a Citation Sentiment Analysis Tool that takes two way path to find the sentiment polarity of a citation. In one direction it uses standard nGram Sentiment Analysis algorithms along with Porter Stemmer and Text Blob. And in second direction it uses Ontology based approach. By extracting verbs from a citation after applying Stemming, Lemmatization and POSTagger, the system creates a weighted match with Ontology for Citation Reasons – OCR to determine its sentiment polarity.
CSAT uses ACL Anthology Network – AAN Citation Dataset that contains 310 Research Papers and 8736 citations and creates a visualization of both techniques and stores it in an RDF based Citation Graph.