Vol.:(0123456789) 1 3 Evolving Systems DOI 10.1007/s12530-017-9188-6 ORIGINAL PAPER Semantic lexicons of English nouns for classifcation Vo Ngoc Phu 1  · Vo Thi Ngoc Tran 2  · Vo Thi Ngoc Chau 3  · Dat Nguyen Duy 4  · Khanh Ly Doan Duy 5   Received: 5 April 2017 / Accepted: 26 May 2017 © Springer-Verlag Berlin Heidelberg 2017 create many English noun phrases based on the English grammars (the English characteristics) and the valences of the English noun phrases are identifed by their specifc contexts. The English noun phrases often bring the seman- tics which the values (or emotional scores) are not fxed and are changed when they appear in their diferent con- texts. Therefore, the results of the sentiment classifcation are not high accuracy if the English noun phrases bring the emotions and their semantic values (or their sentimental scores) are not changed in any context. For those reasons, we propose many rules based on English language gram- mars to calculate the sentimental values of the English noun phrases bearing emotion in their specifc contexts. The results of this work are widely used in applications and researches of the English semantic classifcation. Keywords English emotion dictionary · English sentiment dictionary · English sentiment dictionary · English noun · English grammar · English language characteristic · English sentiment classifcation · English semantic classifcation · English emotion classifcation 1 Introduction There are many applications and many researches on the kind of the emotional vocabulary used to classify senti- ments and opinion mining (positive, negative, neutral) until today. With English language, there is not some research and application made on determining the semantics of Eng- lish terms and especially English noun phrases in the spe- cifc contexts. Sentiment analysis is done by using machine learning methods or methods based on lexicons; or a combination of both. Opinion mining relates to emotion researches that Abstract Sentiment classifcation is studied for a long time and there are many applications and many researches to service communities, commerce, politics, etc. In this research, we propose a new model to calculate the emo- tional values (or semantic scores) of English terms (English verbs, English nouns, English adjectives, English adverbs, etc.) as: frst of all, we build our basis English sentiment dictionary (called bESD) by using Tanimoto Coefcient (Tanimoto measure, called TC) through Google search engine with AND operator and OR operator and then, we * Vo Ngoc Phu vongocphu03hca@gmail.com; vongocphu@dtu.edu.vn Vo Thi Ngoc Tran vtntran@hcmut.edu.vn Vo Thi Ngoc Chau chauvtn@cse.hcmut.edu.vn; chauvtn@hcmut.edu.vn; chauvtn2003@gmail.com Dat Nguyen Duy duydatspk@gmail.com Khanh Ly Doan Duy lykhanhbk@gmail.com 1 Institute of Research and Development, Duy Tan University- DTU, Da Nang, Vietnam 2 School of Industrial Management (SIM), Ho Chi Minh City University of Technology-HCMUT, Vietnam National University, Ho Chi Minh City, Vietnam 3 Computer Science and Engineering (CSE), Ho Chi Minh City University of Technology-HCMUT, Vietnam National University, Ho Chi Minh City, Vietnam 4 Faculty of Information Technology, Ly Tu Trong Technical College, Ho Chi Minh City, Vietnam 5 Faculty of Information Technology, Ho Chi Minh City University of Foreign Languages, Ho Chi Minh City, Vietnam