Applying skip-gram word estimation and SVM-based classification for opinion mining Vietnamese food places text reviews

Abstract

In this paper, a framework for mining unstructured documents in the form of Vietnamese text comments about locations is proposed. In the first step, the evaluation of users in the form of text comments will be extracted to produce a set of sentences in Vietnamese standard grammars by web analytic processing. Through the second step, using Skip-gram based model, the similarity between each phrase in sentences will be detected. The core of this research focuses on contributing an approach for word representation that reflects Vietnamese semantic information contexts for analyzing as an input of a machine learning based classification, SVM. The application of this research is applied to the STAAR project's opinion mining system.

A Transformation Method for Aspect-Based Sentiment Analysis

“…As the rapid development of Vietnamese sentiment analysis, many researchers focused on developing methods on the different domain. For instance, [15] examined a semantic information representation method of words using skip-gram models and SVM to classify them; [5] presented an empirical study on machine learning (Naive Bayes, Maximum Entropy and SVM) based sentiment analysis for Vietnamese, which fo-cuses on sentiment classification on the hotel domain. [10] proposed the semi-supervised learning GK-LDA method for aspect extraction and classification tasks.…”

A CURE Algorithm for Vietnamese Sentiment Classification in a Parallel Environment

“…Much recent research has addressed sentiment classification (Manek et al, 2016;Agarwal and Mittal, 2016a;2016b;Canuto et al, 2016;Ahmed and Danti, 2016;Phu and Tuoi, 2014;Tran et al, 2014;Phu et al, 2016;Phu et al, 2017a;2017b) such as a Gini-Indexbased feature selection method with an SVM classifier for a large movie review data set (Manek et al, 2016), as well as a corpus-based semantic orientation approach for sentiment analysis (Agarwal and Mittal, 2016b). Furthermore, several studies have recently investigated Vietnamese sentiment classification (Ha et al, 2011;Bang et al, 2015;Kieu and Pham, 2010;Vu and Park, 2014;Hoanh-Su et al, 2015;Anh and Dau, 2014;Phan and Cao, 2014;Duyen et al, 2014;Bach et al, 2015;Trinh et al, 2016). Researchers have proposed various methods to address such data sets, including an upgrading FOMS model on Vietnamese reviews on mobile phone products (Ha et al, 2011) and an improved technique to analyze sentiment for Vietnamese texts based on the term feature selection approach (Bang et al, 2015).…”

“…Our research Our model's merits and demerits are illustrated in the Conclusion section. Table 8: Comparisons of our model with the latest Vietnamese sentiment classification models (or the latest Vietnamese sentiment classification methods) in (Ha et al, 2011;Bang et al, 2015;Kieu and Pham, 2010;Xuan-Son Vu and Park, 2014;Le et al, 2015;Trinh and Dau, 2014;Hoanh-Su et al, 2015;Phan and Cao, 2014;Duyen et al, 2014;Bach et al, 2015;Son Trinh et al, 2016) Studies CA SC L SD DT PNE Approach (Ha et al, 2011) No Yes VL Yes Yes No +HAC clustering +Semi-supervised SVM-kNN classification (Bang et al, 2015) No Yes VL Yes Yes No +Decision Tree +Naive Bayes (NB) +Support Vector Machines (SVM +Feature selection technique, χ2 (CHI). (Kieu and Pham, 2010) No Yes VL Yes Yes No A rule-based system using the Gate framework (Vu and Park, 2014) No Yes VL No No No A method to construct VSWN from a Vietnamese dictionary, not from WordNet.…”

“…Our model is quite different from other studies related to Vietnamese vectors, Vietnamese segments, etc. (Hoang et al, 2007;Le et al, 2008;Nguyen et al, 2009), research related to the CURE algorithm (Guha et al, 1998;Yan-Hua et al, 2011;Nian-yun et al, 2009;Ertöz et al, 2002;Kaya and Alhajj, 2005;Ying et al, 2008;Rani et al, 2014), recent studies about Vietnamese sentiment classification (Ha et al, 2011;Bang et al, 2015;Kieu and Pham, 2010;Vu and Park, 2014;Hoanh-Su et al;Anh and Dau, 2014;Phan and Cao, 2014;Duyen et al, 2014;Bach et al, 2015;Trinh et al, 2016), sentiment classification (Manek et al, 2016;Agarwal and Mittal, 2016a;2016b;Canuto et al, 2016;Ahmed and Danti, 2016;Phu and Tuoi, 2014;Tran et al, 2014;Phu et al, 2016;Phu et al, 2017a;2017b) and unsupervised classification (Turney, 2002;Lee et al, 2002a;van Zyl, 2002;Hegarat-Mascle et al, 2002;Ferro-Famil et al, 2002;Chaovalit and Zhou, 2005;Lee et al, 2002b;Gllavata et al, 2004).…”

Aspect Analysis for Opinion Mining of Vietnamese Text

“…For Vietnamese text, Phan et al (2014) [18] focuses on an approach to word representation and use this as an input of SVM (Support Vector Machine) which is a machine learning based classification. Our work takes a major step further which is not only for aspect extraction but also for aspect classification.…”