Abstract:In this paper, we propose a new method for the opinion sentence extraction and its polarity identification in sentences which contain sentimental elements. In this method, the single sentimental element and Composite Sentimental Element are calculated respectively by sentimental dictionary and sentiment-based training corpus. After that, we design a model which is to extract objective & subjective sentences and analyze the polarity of the latter. This model can be used to extract the sentimental informatio… Show more
“…The study found that the use of sentimental words to classify emotional tendency is hard to fulfill the needs of the relative emotion discrimination task. Therefore, scholars have proposed the task of sentimental element extraction [34], [35]. The emotional element extraction task is also called fine-grained opinion mining, and most of its related work is to do sequence labeling.…”
Section: ) Label Sentimental Elements Automaticallymentioning
Topical influencers are experts on a specific topic, who always play an important role in the opinion dissemination. From the perspective of influence polarity, topical influencers can be classified into opinion leaders who gain a great deal of support, trolls who are widely condemned, and controversial figures who trigger debate. In this paper, discriminating topical influencers of social networks are addressed. First, the trained BiLSTM-CRF model is constructed to extract emotional elements, and, then, the proposed emotional matching and emotional transforming algorithms are leveraged to obtain the relative emotion of users. Second, the rank of influencers is calculated by the quantified user behavior characteristics and the multi-centrality algorithm. Finally, according to relative emotion of users, the topical influencers are divided into three categories-opinion leaders, trolls, and controversial figures. Experimental results show that the user relative sentiment analysis method proposed in this paper has higher accuracy, and the empirical analysis manifests that the three kinds of influencers affect the opinion distribution in various degrees.
“…The study found that the use of sentimental words to classify emotional tendency is hard to fulfill the needs of the relative emotion discrimination task. Therefore, scholars have proposed the task of sentimental element extraction [34], [35]. The emotional element extraction task is also called fine-grained opinion mining, and most of its related work is to do sequence labeling.…”
Section: ) Label Sentimental Elements Automaticallymentioning
Topical influencers are experts on a specific topic, who always play an important role in the opinion dissemination. From the perspective of influence polarity, topical influencers can be classified into opinion leaders who gain a great deal of support, trolls who are widely condemned, and controversial figures who trigger debate. In this paper, discriminating topical influencers of social networks are addressed. First, the trained BiLSTM-CRF model is constructed to extract emotional elements, and, then, the proposed emotional matching and emotional transforming algorithms are leveraged to obtain the relative emotion of users. Second, the rank of influencers is calculated by the quantified user behavior characteristics and the multi-centrality algorithm. Finally, according to relative emotion of users, the topical influencers are divided into three categories-opinion leaders, trolls, and controversial figures. Experimental results show that the user relative sentiment analysis method proposed in this paper has higher accuracy, and the empirical analysis manifests that the three kinds of influencers affect the opinion distribution in various degrees.
“…Since the enormous amount of users and its great effect, people find it necessary to take an insight look at this new form of message. Researches on microblogs fall into multiple areas, such as extraction of messages (Liu et al, 2012), extraction of opinion sentence (Ding, Liu, 2008;Liu et al, 2013), and determination of sentiment orientation (Ding, Liu, 2008;Go et al, 2009;Zhang et al, 2014). Generally speaking, researchers want to find out what people think through what they post on Weibo platform.…”
This paper presents our Chinese microblog sentiment classification (CMSC) system in the Topic-Based Chinese Message Polarity Classification task of SIGHAN-8 Bake-Off. Given a message from Chinese Weibo platform and a topic, our system is designed to classify whether the message is of positive, negative, or neutral sentiment towards the given topic. Due to the difficulties like the out-ofvocabulary Internet words and emoticons, polarity classification of Chinese microblogs is still an open problem today. In our system, Maximum Entropy (MaxEnt) is employed, which is a discriminative model that directly models the class posteriors, allowing them to incorporate a rich set of features. Moreover, oversampling approach is used to hand the unbalance problem. Evaluation results demonstrate the utility of our system, showing an accuracy of 66.4% for restricted resource and 66.6% for unrestricted resource.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.