Emotion analysis in blogs at sentence level using a Chinese emotion corpus

Quan, Changqin; He, Tingting; Ren, Fuji

doi:10.1109/nlpke.2010.5587790

Cited by 6 publications

(4 citation statements)

References 16 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate proposed method, we conduct experiments on the Ren‐CECps corpus, 32 which is commonly used in emotion classification. This corpus contains 35 096 sentences from blogs, and each sentence is marked with eight emotion labels.…”

Section: Methodsmentioning

confidence: 99%

Interdisciplinary knowledge‐based implicit emotion recognition

Jiang

Wang

Luo

2020

Concurrency and Computation

View full text Add to dashboard Cite

Detecting different emotions is a key step toward intelligent recommendation and affective computing, which plays an increasingly important role in guiding decisions. There have been a large number of previous work of machine learning in this topic. However, most existing methods neglect the help of long-term accumulated and precious interdisciplinary knowledge, which cover both computer science and psychology. In this work, we distill part of the psychological knowledge as following: (i) The emotions with the same polarity co-occur frequently, while emotions with contrary polarity co-exist hardly; (ii) The relations between emotions are variable and complicated; (iii) The number of emotions that can be aroused in the same moment is limited. In this paper, we propose two novel modules to execute above prior knowledge, by adding external constraints to our proposed model Double Attention Convolutional Neural Network. In the first module, the emotion relationships are captured by an automatically extracted emotion template. In the second module, uncertainty punishment is applied to limit the too frequent emotions. Our proposed model, which employs interdisciplinary knowledge, performs potentially and get state-of-the-art result when compared with models without above constraints.

show abstract

Section: Methodsmentioning

confidence: 99%

Interdisciplinary knowledge‐based implicit emotion recognition

Jiang

Wang

Luo

2020

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…In line with the features of cyberbullying words in Chinese, cyberbullying behaviour also contains emotions (den Hamer and Konijin, 2016). In relevant emotion theories, humans' emotional states were categorised into acceptance, anger, anticipation, disgust, joy, fear, sadness and surprise (Ekman, 1992), and in China, inspirational words were divided into four categories, including joy, love, expectation and surprise, and the frustrating words were summarised into anxiety, sorrow, anger and hate (Quan et al, 2010). Previous studies pointed out that cyberbullying was a phenomenon that was strongly associated with "anger," "fear" and "disgust" (Vranjes et al, 2017).…”

Section: Cyberbullying Phenomenon Globally and In Chinamentioning

confidence: 99%

Cognition and gender differences in cyberbullying in China: an investigation of textual cues and sentimental clues

Li,

Peng

2023

OIR

View full text Add to dashboard Cite

Purpose Cyberbullying is a globally pervasive problem and not novel in academia. Previous studies mainly focussed on the features, consequences and technological management of cyberbullying. However, most of the studies took cyberbullying examples in the West, and some issues still need to be addressed in the Chinese context. Thus, this study investigates how participants use cyberbullying words and why they use them in that particular way in China.Design/methodology/approach This study uses content analysis to summarise the typical features of cyberbullying words, revealing a positive relationship between cyberbullying words and sentimental expressions. This paper also uses the questionnaire (N = 705) to explore the prevalence of cyberbullying among Chinese Internet users and to compare the gender differences in the cognition of cyberbullying words and involvement in cyberbullying, in line with the social cognitive theory.Findings This study stated that people prefer repetitively using offensive words to achieve cyberbullying goals. Interestingly, this study does not find obvious gender differences in cyberbullying roles and cyberbullying language use. However, it explained the relationship between cognition and the use of cyberbullying words from a gender perspective.Practical implications Theoretically, this study expands cyberbullying studies into a new cultural environment, pointing to a novel term, “imbalanced relation,” for exploring cyberbullying behaviours. This study highlights the significance of technology and education in detecting and preventing cyberbullying, suggesting that educators and social media platforms can directly predict and prevent cyberbullying through textual perspectives and individuals' cognition of cyberbullying.Originality/value This study aims to examine cyberbullying linguistic and emotional features and individual differences in cyberbullying behaviour in a high-context culture like China. Its values include comparing the differences between cyberbullying in China and cyberbullying in the West from the linguistic and cultural directions and reconsidering the “power imbalance” feature of cyberbullying.

show abstract

“…By manually labeling the corpus in advance, the machine can automatically learn the rules, train a classification model and then use the trained model to classify the test data to assess the model’s accuracy (Singh et al , 2021). Sentence level sentiment analysis is based on word-level sentiment analysis; it then adds the sentence’s grammatical structure, such as turning sentence, question sentence, rhetorical question sentence, exclamatory sentence or negative sentence (Chen et al , 2017; Quan et al , 2010; Rui et al , 2009). According to the sentence structure and emotional polarity of the words in it, the emotional tendency of the whole sentence is calculated (Yuan and Hongfei, 2011).…”

Section: Measuring Corporate Image Through Automated Textual Analysismentioning

confidence: 99%

“…In addition, the degree adverbs were given different weights (Table 5). Then, a sentence’s sentiment was calculated based on sentence structure, giving different weights to particular sentence types (Quan et al , 2010) (Table 6). Finally, sentence’s sentiment was summarized to obtain the comment’s sentiment.…”

Section: Measuring Corporate Image Through Automated Textual Analysismentioning

confidence: 99%

Generating business intelligence through automated textual analysis: measuring corporate image with online information

Peng

Wan

2022

CMS

View full text Add to dashboard Cite

Purpose In this age of extremely well-developed social media, it is necessary to detect any change in the corporate image of an enterprise immediately so as to take quick action to avoid the wide spread of a negative image. However, existing survey-based corporate image evaluation methods are costly, slow and static, and the results may quickly become outdated. User comments, news reports and we-media articles on the internet offer varied channels for enterprises to obtain public evaluations and feedback. The purpose of this study is to effectively use online information to timely and accurately measure enterprises’ corporate images. Design/methodology/approach A new corporate image evaluation method was built by first using a literature review to establish a corporate image evaluation index system. Next, an automatic text analysis of online public information was performed through a topic classification and sentiment analysis algorithm based on the dictionary. The accuracy of the topic classification and sentiment analysis algorithm is then calculated. Finally, three internet enterprises were chosen as cases, and their corporate image was evaluated. Findings The results show that the author’s corporate image evaluation method is effective. Originality/value First, in this study, a new corporate image evaluation index system is constructed. Second, a new corporate image evaluation method based on text mining is proposed that can support data-driven decision-making for managers with real-time corporate image evaluation results. Finally, this study improves the understanding of corporate image by generating business intelligence through online information. The findings provide researchers with specific and detailed suggestions that focus on the corporate image management of emerging internet enterprises.

show abstract

Emotion analysis in blogs at sentence level using a Chinese emotion corpus

Cited by 6 publications

References 16 publications

Interdisciplinary knowledge‐based implicit emotion recognition

Interdisciplinary knowledge‐based implicit emotion recognition

Cognition and gender differences in cyberbullying in China: an investigation of textual cues and sentimental clues

Generating business intelligence through automated textual analysis: measuring corporate image with online information

Contact Info

Product

Resources

About