With the rising and spreading of micro-blog, the sentiment classification of short texts has become a research hotspot. Some methods have been developed in the past decade. However, since the Chinese and English are d...With the rising and spreading of micro-blog, the sentiment classification of short texts has become a research hotspot. Some methods have been developed in the past decade. However, since the Chinese and English are different in language syntax, semantics and pragmatics, sentiment classification methods that are effective for English twitter may fail on Chinese micro-blog. In addition, the colloquialism and conciseness of short Chinese texts introduces additional challenges to sentiment classification. In this work, a novel hybrid learning model was proposed for sentiment classification of Chinese micro-blogs, which included two stages. In the first stage, emotional scores were calculated over the whole dataset by utilizing an improved Chinese-oriented sentiment dictionary classification method. Data with extremely high or low scores were directly labeled. In the second stage, the remaining data were labeled by using an integrated classification method based on sentiment dictionary, support vector machine(SVM) and k-nearest neighbor(KNN). An improved feature selection method was adopted to enhance the discriminative power of the selected features. The two-stage hybrid framework made the proposed method effective for sentiment classification of Chinese micro-blogs. Experiments on the COAE2014(Chinese Opinion Analysis Evaluation 2014) dataset show that the proposed method outperforms other schemes.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
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
This paper builds the structure of the vector autoregression( SVAR) model short-term constraints and studies the interactive mechanism of investor sentiment,monetary policy and stock market from 2008 to 2016. The resu...This paper builds the structure of the vector autoregression( SVAR) model short-term constraints and studies the interactive mechanism of investor sentiment,monetary policy and stock market from 2008 to 2016. The result finds that investor sentiment, currency liquidity and stock market gains a significant asymmetric effect. First,the interaction effects of investor sentiment and stock market are positive feedback mechanism, and investor sentiment significantly affects the stock market in the short term. Furthermore,monetary policy and stock market has a positive role in promoting each other. Finally, investor sentiment shows negative feedback mechanism of monetary policy.展开更多
股票市场的不确定性和复杂性使得股票预测成为一项具有挑战性的任务。鉴于金融文本在股票预测中的潜在价值,采用词典法和BERT双向长短期记忆模型(bidirectional encoder representations from transformers-bidirectional long short-te...股票市场的不确定性和复杂性使得股票预测成为一项具有挑战性的任务。鉴于金融文本在股票预测中的潜在价值,采用词典法和BERT双向长短期记忆模型(bidirectional encoder representations from transformers-bidirectional long short-term memory,BERT-BiLSTM)对在线财经新闻提取情感特征,构建了融合情感特征和股票交易特征的股指预测模型。实验对比了融合情感特征前后模型的预测能力,并探讨了不同模型、不同时间周期下预测能力的差异。实验结果表明,融合词典法和深度学习技术提取的情感特征均能提升各模型股指预测的准确率。LSTM模型相较其他实验模型在融合情感特征前后的股指预测上均表现较好。进一步的时间跨度分析表明,股指预测模型在较短的时间跨度上对股票指数涨跌的预测能力更强。为验证股指预测模型的实际价值,对沪深300指数的牛熊市和震荡市进行回测分析,结合LSTM模型和深度Q网络(deep Q-network,DQN)原理,对比了传统均线策略以及结合DQN强化学习算法后股指回测差异。回测结果表明,相比于单一的传统交易策略,结合传统交易策略和深度学习方法的股票指数预测模型在牛熊市及震荡市中均保证了正的夏普比例和累积收益率,并有效控制了最大回撤,显示出更强的市场适应性和盈利能力。展开更多
基金Projects(61573380,61303185)supported by the National Natural Science Foundation of ChinaProject(13BTQ052)supported by the National Social Science Foundation of China+1 种基金Project(2016M592450)supported by the China Postdoctoral Science FoundationProject(2016JJ4119)supported by the Hunan Provincial Natural Science Foundation of China
文摘With the rising and spreading of micro-blog, the sentiment classification of short texts has become a research hotspot. Some methods have been developed in the past decade. However, since the Chinese and English are different in language syntax, semantics and pragmatics, sentiment classification methods that are effective for English twitter may fail on Chinese micro-blog. In addition, the colloquialism and conciseness of short Chinese texts introduces additional challenges to sentiment classification. In this work, a novel hybrid learning model was proposed for sentiment classification of Chinese micro-blogs, which included two stages. In the first stage, emotional scores were calculated over the whole dataset by utilizing an improved Chinese-oriented sentiment dictionary classification method. Data with extremely high or low scores were directly labeled. In the second stage, the remaining data were labeled by using an integrated classification method based on sentiment dictionary, support vector machine(SVM) and k-nearest neighbor(KNN). An improved feature selection method was adopted to enhance the discriminative power of the selected features. The two-stage hybrid framework made the proposed method effective for sentiment classification of Chinese micro-blogs. Experiments on the COAE2014(Chinese Opinion Analysis Evaluation 2014) dataset show that the proposed method outperforms other schemes.
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.
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Supported by National High Technology Research and Development Program of China （863 Program） （2008AA01Z144） National Natural Science Foundation of China （60803093 60975055）
文摘This paper builds the structure of the vector autoregression( SVAR) model short-term constraints and studies the interactive mechanism of investor sentiment,monetary policy and stock market from 2008 to 2016. The result finds that investor sentiment, currency liquidity and stock market gains a significant asymmetric effect. First,the interaction effects of investor sentiment and stock market are positive feedback mechanism, and investor sentiment significantly affects the stock market in the short term. Furthermore,monetary policy and stock market has a positive role in promoting each other. Finally, investor sentiment shows negative feedback mechanism of monetary policy.
文摘股票市场的不确定性和复杂性使得股票预测成为一项具有挑战性的任务。鉴于金融文本在股票预测中的潜在价值,采用词典法和BERT双向长短期记忆模型(bidirectional encoder representations from transformers-bidirectional long short-term memory,BERT-BiLSTM)对在线财经新闻提取情感特征,构建了融合情感特征和股票交易特征的股指预测模型。实验对比了融合情感特征前后模型的预测能力,并探讨了不同模型、不同时间周期下预测能力的差异。实验结果表明,融合词典法和深度学习技术提取的情感特征均能提升各模型股指预测的准确率。LSTM模型相较其他实验模型在融合情感特征前后的股指预测上均表现较好。进一步的时间跨度分析表明,股指预测模型在较短的时间跨度上对股票指数涨跌的预测能力更强。为验证股指预测模型的实际价值,对沪深300指数的牛熊市和震荡市进行回测分析,结合LSTM模型和深度Q网络(deep Q-network,DQN)原理,对比了传统均线策略以及结合DQN强化学习算法后股指回测差异。回测结果表明,相比于单一的传统交易策略,结合传统交易策略和深度学习方法的股票指数预测模型在牛熊市及震荡市中均保证了正的夏普比例和累积收益率,并有效控制了最大回撤,显示出更强的市场适应性和盈利能力。
