Abstract
Sentiment Analysis is an important research direction of natural language processing, and it is widely used in politics, news and other fields. Word embeddings play a significant role in sentiment analysis. The existing sentiment embeddings methods directly embed the sentiment lexicons into traditional word representation. This sentiment representation methods can only differentiate the sentiment information of different words, not the same word in different contexts, so it cannot provide accurate sentiment information for word in different contexts. This paper proposes sentiment concept to solve the problem. First, we found the optimal sentiment concept of words in Microsoft Concept Graph according to the context of words. Then we obtained the sentiment information of words under optimal sentiment concept from the multi-semantics sentiment intensity lexicon which we constructed in this paper to achieve accurate embedding of sentiment information and provide more accurate semantics and sentiment representation for words. Finally, we combined two refined word embeddings methods to achieve a more comprehensive word representation. Compared with traditional and sentiment embeddings methods on six representative datasets, the validity of the word embeddings method based on sentiment concept proposed in this paper is verified.
Highlights
Sentiment Analysis is a technology that automatically extracts sentiment information from unstructured texts
This paper proposes sentiment concept to solve the problem, we find out the optimal sentiment concept for the word according to the context to provide more accurate semantics and sentiment representation, and further improve the accuracy of Sentiment Analysis
The detailed process is as follows: (1) Traverse the sentiment lexicon Fusion Sentiment Intensity Lexicon (FSIL) to judge whether wi is a sentiment word or not; (2) If wi is a sentiment word, we find the optimal sentiment concept coptimal of wi from Microsoft Concept Graph; (3) Select TOPk similar words with the highest semantic similarity under coptimal of wi; (4) Find the sentiment intensity score under coptimal of wi and TOPk in FSIL, and reorder TOPk according to the sentiment intensity difference between TOPk and wi
Summary
Sentiment Analysis is a technology that automatically extracts sentiment information from unstructured texts. The idea is that words with similar contexts have similar vector representations It is very useful for many tasks which related to semantic similarity because it can capture lots of contextual features to represent texts. This paper proposes sentiment concept to solve the problem, we find out the optimal sentiment concept for the word according to the context to provide more accurate semantics and sentiment representation, and further improve the accuracy of Sentiment Analysis. Precise semantics and sentiment representations for words, (2) constructing a sentiment intensity lexicon containing singlesemantics and multi-semantics sentiment words through the multi-semantics integration of six representative sentiment intensity lexicons, to provide more accurate sentiment information for words with different semantics, (3) RefinedWord2Vec and Refined-GloVe we improved are averaged to obtain Refined Global Word Embeddings(RGWE).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
