Nowadays,the impact of emerging social media on the accounting is still a relatively new field and none of the existing research has explored the correlation among the public attitude towards social media,official acc...Nowadays,the impact of emerging social media on the accounting is still a relatively new field and none of the existing research has explored the correlation among the public attitude towards social media,official accounting attitude and the performance of the stock prices of listed firms.U sing the state-of-the-art sentiment analysis tool and 25 public companies'dataset from Yahoo Finance,the correlations among the company's stock price,sentiment in twitter and sentiment in earnings report are quantitatively studied in this paper.Hypothesis testing is used to infer the result of two proposed hypotheses on the sample data.The results demonstrate that(1)there is a significant negative correlation between company's stock price and sentiment in its corresponding earnings reports,and(2)there is no statistical significance for the correlation between company's stock price and sentiment in its corresponding Twitter data.展开更多
Sentiment analysis is the computational study of how opinions, attitudes, emotions, and perspectives are expressed in language, and has been the important task of natural language processing. Sentiment analysis is hig...Sentiment analysis is the computational study of how opinions, attitudes, emotions, and perspectives are expressed in language, and has been the important task of natural language processing. Sentiment analysis is highly valuable for both research and practical applications. The focuses were put on the difficulties in the construction of sentiment classifiers which normally need tremendous labeled domain training data, and a novel unsupervised framework was proposed to make use of the Chinese idiom resources to develop a general sentiment classifier. Furthermore, the domain adaption of general sentiment classifier was improved by taking the general classifier as the base of a self-training procedure to get a domain self-training sentiment classifier. To validate the effect of the unsupervised framework, several experiments were carried out on publicly available Chinese online reviews dataset. The experiments show that the proposed framework is effective and achieves encouraging results. Specifically, the general classifier outperforms two baselines(a Na?ve 50% baseline and a cross-domain classifier), and the bootstrapping self-training classifier approximates the upper bound domain-specific classifier with the lowest accuracy of 81.5%, but the performance is more stable and the framework needs no labeled training dataset.展开更多
针对目前多模态情感分析在处理模态间交互作用及捕捉模态异质性不充分导致分类结果不准确的问题,提出一种基于反馈机制及特征分解的多模态情感分析模型(feedback mechanism and feature decomposition,FMFD)。该模型整合了反馈机制与对...针对目前多模态情感分析在处理模态间交互作用及捕捉模态异质性不充分导致分类结果不准确的问题,提出一种基于反馈机制及特征分解的多模态情感分析模型(feedback mechanism and feature decomposition,FMFD)。该模型整合了反馈机制与对比特征分解技术,采用反馈模块实现跨模态互动,并通过特征掩码调优输入的模态信息。通过特征分解器将模态信息细分为模态共同特征和模态特定特征,并引入层次对比学习损失函数来强化这些特征,从而捕获不同模态及样本间的相似性和异质性,以便实现多模态特征融合与情感预测任务。在3个标准数据集上的实验结果表明,该模型在多项评价指标上优于其它使用方法,验证了该模型在多模态情感分析方面的有效性。展开更多
文摘Nowadays,the impact of emerging social media on the accounting is still a relatively new field and none of the existing research has explored the correlation among the public attitude towards social media,official accounting attitude and the performance of the stock prices of listed firms.U sing the state-of-the-art sentiment analysis tool and 25 public companies'dataset from Yahoo Finance,the correlations among the company's stock price,sentiment in twitter and sentiment in earnings report are quantitatively studied in this paper.Hypothesis testing is used to infer the result of two proposed hypotheses on the sample data.The results demonstrate that(1)there is a significant negative correlation between company's stock price and sentiment in its corresponding earnings reports,and(2)there is no statistical significance for the correlation between company's stock price and sentiment in its corresponding Twitter data.
基金Projects(61170156,60933005)supported by the National Natural Science Foundation of China
文摘Sentiment analysis is the computational study of how opinions, attitudes, emotions, and perspectives are expressed in language, and has been the important task of natural language processing. Sentiment analysis is highly valuable for both research and practical applications. The focuses were put on the difficulties in the construction of sentiment classifiers which normally need tremendous labeled domain training data, and a novel unsupervised framework was proposed to make use of the Chinese idiom resources to develop a general sentiment classifier. Furthermore, the domain adaption of general sentiment classifier was improved by taking the general classifier as the base of a self-training procedure to get a domain self-training sentiment classifier. To validate the effect of the unsupervised framework, several experiments were carried out on publicly available Chinese online reviews dataset. The experiments show that the proposed framework is effective and achieves encouraging results. Specifically, the general classifier outperforms two baselines(a Na?ve 50% baseline and a cross-domain classifier), and the bootstrapping self-training classifier approximates the upper bound domain-specific classifier with the lowest accuracy of 81.5%, but the performance is more stable and the framework needs no labeled training dataset.
基金Supported by National High Technology Research and Development Program of China （863 Program） （2008AA01Z144） National Natural Science Foundation of China （60803093 60975055）
文摘针对目前多模态情感分析在处理模态间交互作用及捕捉模态异质性不充分导致分类结果不准确的问题,提出一种基于反馈机制及特征分解的多模态情感分析模型(feedback mechanism and feature decomposition,FMFD)。该模型整合了反馈机制与对比特征分解技术,采用反馈模块实现跨模态互动,并通过特征掩码调优输入的模态信息。通过特征分解器将模态信息细分为模态共同特征和模态特定特征,并引入层次对比学习损失函数来强化这些特征,从而捕获不同模态及样本间的相似性和异质性,以便实现多模态特征融合与情感预测任务。在3个标准数据集上的实验结果表明,该模型在多项评价指标上优于其它使用方法,验证了该模型在多模态情感分析方面的有效性。
