Historical credibility for movie reviews and its application to weakly supervised classification

Kim, Min-Seon; Lim, Bo-Young; Shin, Hansub; Kwon, Hyuk-Yoon

doi:10.1016/j.ins.2023.01.138

Cited by 4 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some studies argue that the comments and review sentiments may be difficult to analyze since the number of reviews is large. Some sentiments of the information delivered are vague, and difficult to make a judgment [40] . Rather than using the sentiment to judge, the number of reviews could deliver some information.…”

Section: Heterogeneity Analysis and Comments Credibilitymentioning

confidence: 99%

Culture and social well-being value cognition, a comparative study of social preference from movie reviews

Sheng,

Shen,

Zheng

2023

Environ Soc Psychol

View full text Add to dashboard Cite

Analyzing the Japanese movie reviews given by both Chinese and Japanese movie followers, this research provides empirical evidence to explore the cultural and social well-being diversified preference. The results show that cultural inspiration and social well-being have a significant influence on movie reviews and preferences. The more collectivist Chinese followers prefer starring and giving their comments to the movies. Whereas even Japanese reviewers give their review scores, but they are more uncertain to share their feelings to praise or blame the high and low-score movies. The findings reflect the culture and social value and provide considerable social policy decision-making significance to increase social well-being sustainability.

show abstract

Section: Heterogeneity Analysis and Comments Credibilitymentioning

confidence: 99%

Culture and social well-being value cognition, a comparative study of social preference from movie reviews

Sheng,

Shen,

Zheng

2023

Environ Soc Psychol

View full text Add to dashboard Cite

show abstract

“…Each approach can be applied according to the research domain being worked on. The supervised learning approach is known as the machine learning development process, which requires labeled data [5][6][7], while unsupervised learning is without labeled data [8][9][10]. Supervised learning is applied to develop classification models and requires labeled data.…”

Section: Introductionmentioning

confidence: 99%

Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method

Chamid,

Widowati,

Kusumaningrum

2024

ISI

View full text Add to dashboard Cite

Classification is part of machine learning, and developing it requires labeled data. Most data is available in an unlabeled form. Data labeling is a step that researchers must take. Good labeled data will produce a good classification model. The data labeling process cannot be ignored and needs to be done carefully and consistently. Because the classification process requires well-labeled data that can be accounted for. In addition, good labeled data will produce a good classification model. The role of an expert (rater) is needed to label the data and ideally at least two experts. However, involving two raters will become a new problem because it is likely that the results of the inter-rater labeling will be different. We propose the Cohen Kappa method to overcome this problem. We used data from scraping user reviews of the Indonesian marketplace, there were 4.307. Based on the calculation results, Kappa=0.909 for aspect detection, Kappa=0.893 for sentiment classification, and Kappa=0.971 for class aspect. Based on the kappa value, the labeling results for aspect detection, sentiment classification and aspect class were declared "almost perfect agreement", so that the results of this research obtained labeled data that can be used for classification tasks, especially for developing aspect-based sentiment analysis models.

show abstract

Two-way deviation: the impact of the deviation of horizontal and vertical answers on knowledge adoption in virtual Q&A communities

Li,

Liang

2024

LHT

View full text Add to dashboard Cite

PurposeKnowledge adoption is the key to effective knowledge exchange in virtual question-and-answer (Q&A) communities. Although previous studies have examined the effects of knowledge content, knowledge source credibility and the personal characteristics of knowledge seekers on knowledge adoption in virtual Q&A communities from a static perspective, the impact of answer deviation on knowledge adoption has rarely been explored from a context-based perspective. The purpose of this study is to explore the impact of two-way deviation on knowledge adoption in virtual Q&A communities, with the aim of expanding the understanding of knowledge exchange and community management.Design/methodology/approachThe same question and the same answerer often yield multiple answers. Knowledge seekers usually read multiple answers to make adoption decisions. The impact of deviations among answers on knowledge seekers' knowledge adoption is critical. From a context-based perspective, a research model of the impact of the deviation of horizontal and vertical answers on knowledge adoption is established based on the heuristic-systematic model (HSM) and empirically examined with 88,287 Q&A data points and answerer data collected from Zhihu. Additionally, the moderation effects of static factors such as answerer reputation and answer length are examined.FindingsThe negative binomial regression results show that the content and emotion deviation of horizontal answers negatively affect knowledge seekers' knowledge adoption. The content deviation of vertical answers is negatively associated with knowledge adoption, while the emotion deviation of vertical answers is positively related to knowledge adoption. Moreover, answerer reputation positively moderates the negative effect of the emotion deviation of horizontal answers on knowledge adoption. Answer length weakens the negative correlation between the content deviation of horizontal and vertical answers and knowledge adoption.Originality/valueThis study extends previous research on knowledge adoption from a static perspective to a context-based perspective. Moreover, information deviation is expanded from a one-way variable to a two-way variable. The combined effects of static and contextual factors on knowledge adoption are further uncovered. This study can not only help knowledge seekers identify the best answers but also help virtual Q&A community managers optimize community design and operation to reduce the cost of knowledge search and improve the efficiency of knowledge exchange.

show abstract

Historical credibility for movie reviews and its application to weakly supervised classification

Cited by 4 publications

References 42 publications

Culture and social well-being value cognition, a comparative study of social preference from movie reviews

Culture and social well-being value cognition, a comparative study of social preference from movie reviews

Labeling Consistency Test of Multi-Label Data for Aspect and Sentiment Classification Using the Cohen Kappa Method

Two-way deviation: the impact of the deviation of horizontal and vertical answers on knowledge adoption in virtual Q&A communities

Contact Info

Product

Resources

About