
Market Sentiment, Investment Factor and Asset Pricing: Comparative Analysis Based on News and Social Media
Yinggang ZHOU, Chengwei TANG, Zhehui LIN
China Journal of Econometrics ›› 2024, Vol. 4 ›› Issue (3) : 567-587.
Market Sentiment, Investment Factor and Asset Pricing: Comparative Analysis Based on News and Social Media
This paper compares and analyzes the differences in stock pricing between news sentiment and social media sentiment in two different time dimensions, daily and monthly, using individual sentiment data from the Thomson Reuters MarketPsych Indices and trading data from the US stock market from 2010 to 2019. The empirical results indicate that social media sentiment performs better at the daily level than news sentiment, and news sentiment has a stronger explanatory power on stock returns at the monthly level than social media sentiment. Specifically, at the daily level, this paper constructs news sentiment factor and social media sentiment factor, and finds that social media sentiment factor still exhibits significant excess returns under the Fama-French five-factor model, while news sentiment factor no longer exhibits excess returns. In addition, social media sentiment factor can explain most market anomalies at the daily level, while news sentiment factor cannot. In order to investigate the reasons, this paper conducts a Granger causality test, indicating that the response speed of social media sentiment factor is 3 to 4 trading days faster than that of news sentiment factor. At the monthly level, this paper finds that news sentiment improves its ability to explain anomalies, while the explanatory power of social media decreases significantly. In addition, for volatility anomalies and idiosyncratic volatility anomalies, the monthly news sentiment factor has a significant explanatory power, while the explanatory power of the monthly social media sentiment factor is not significant.
social media / news / market sentiment / asset pricing {{custom_keyword}} /
表1 数据介绍 |
数据类型 | 数据频率 | 时间跨度 | 数据来源 |
Sentiment情绪指标 | 日度 | 2010.01.01–2019.12.31 | 汤森路透TRMI |
美股价格数据 | 日度/月度 | 2010.01.01–2019.12.31 | 彭博终端 |
上市公司财务数据 | 月度 | 2010.01.01–2019.12.31 | 彭博终端 |
Fama-French因子数据 | 日度/月度 | 2010.01.01–2019.12.31 | Kenneth R. French |
市场异象数据 | 日度/月度 | 2010.01.01–2019.12.31 | Kenneth R. French |
表2 基于新闻和社交媒体情绪十等分的投资组合的日度结果 |
低 | 3 | 5 | 7 | 9 | 高 | 高-低 | |
平均收益率 | 0.00 | 0.06*** | 0.17*** | 0.25*** | 0.15*** | 0.16*** | |
( | ( | (2.97) | (8.50) | (11.76) | (7.44) | (16.61) | |
夏普比率 | 0.00 | 0.03*** | 0.07*** | 0.10*** | 0.07*** | 0.07*** | |
(0.09) | ( | (3.69) | (8.13) | (10.53) | (7.51) | (12.89) | |
低 | 3 | 5 | 7 | 9 | 高 | 高-低 | |
平均收益率 | 0.05** | 0.23*** | 0.21*** | 0.13*** | 0.18*** | ||
( | ( | (2.45) | (11.76) | (10.74) | (6.47) | (19.45) | |
夏普比率 | 0.01 | 0.08*** | 0.09*** | 0.06*** | 0.07*** | ||
( | ( | (1.47) | (11.88) | (10.98) | (6.70) | (14.01) |
注: 括号中的数字为 |
表3 基于日度情绪划分的投资组合 |
高 | 中 | 低 | 高 | 中 | 低 | ||
市值 | |||||||
小 | 0.109*** | ||||||
( | ( | ( | ( | ( | ( | ||
中 | 0.020 | 0.004 | 0.039 | 0.005 | |||
(0.72) | ( | (0.12) | (1.36) | (0.16) | ( | ||
大 | 0.039* | 0.033 | 0.041* | 0.041* | 0.040* | 0.037* | |
(1.82) | (1.52) | (1.90) | (1.86) | (1.81) | (1.67) |
注: 括号中的数字为 |
表4 基于新闻和社交媒体情绪十等分的投资组合的日度结果 |
样本数 | 均值 | 标准差 | 中位数 | 最小值 | 最大值 | 偏度 | 峰度 | |
新闻情绪因子 | 2516 | 1.04 | 0.01 | 8.05 | 42.14 | |||
社交媒体情绪因子 | 2516 | 0.05 | 0.78 | 0.05 | 5.88 | 0.37 | 7.01 | |
新闻情绪因子 | ||||||||
社交媒体情绪因子 | ||||||||
均值 |
注: 括号中的数字为 |
表5 新闻情绪因子和社交媒体情绪因子是否存在超额收益? |
新闻情绪因子 | 社交媒体情绪因子 | |
Fama-French三因子模型 | 0.05*** | |
( | (3.15) | |
Fama-French五因子模型 | 0.05*** | |
( | (3.04) |
注: 括号中的数字为 |
表6 新闻情绪因子解释基于市值和社交媒体情绪的投资组合(单位: %) |
社交媒体情绪 | 高 | 中 | 低 | |
市值 | 小 | |||
( | ( | ( | ||
中 | ||||
( | ( | ( | ||
大 | ||||
( | ( | ( | ||
市值 | 小 | |||
( | ( | ( | ||
中 | ||||
( | ( | ( | ||
大 | ||||
( | ( | ( | ||
市值 | 小 | 4.265 | 1.416 | |
(1.58) | (0.53) | ( | ||
中 | 0.422 | 4.533* | ||
(0.44) | ( | (1.93) | ||
大 | 0.924** | 0.579 | ||
(2.10) | (1.39) | ( |
注: 括号中的数字为 |
表7 社交媒体情绪因子解释基于社交媒体情绪的投资组合(单位: %) |
新闻媒体情绪 | 高 | 中 | 低 | |
市值 | 小 | |||
( | ( | ( | ||
中 | ||||
( | ( | ( | ||
大 | ||||
( | ( | ( | ||
市值 | 小 | |||
( | ( | ( | ||
中 | ||||
( | ( | ( | ||
大 | ||||
( | ( | ( | ||
市值 | 小 | 5.130 | ||
(0.91) | ( | ( | ||
中 | ||||
( | ( | ( | ||
大 | 0.223 | |||
(0.40) | ( | ( |
注: 括号中的数字为 |
表8 日度情绪因子对市场异象的解释能力 |
账面市值比 | 投资 | 盈利 | 动量 | 短期反转 | 长期反转 | |
社交媒体情绪因子 | 0.80* | 4.06** | 6.40*** | 4.75*** | ||
( | ( | (1.81) | (2.53) | (3.15) | (4.58) | |
新闻情绪因子 | 0.23 | 0.42 | 1.63 | 1.31 | 0.24 | |
( | (0.83) | (1.28) | (1.36) | (0.87) | (0.31) | |
控制FF5因子 | 是 | 是 | 是 | 是 | 是 | 是 |
注: 括号中的数字为 |
表9 新闻和社交媒体情绪因子格兰杰检验结果 |
滞后1期 | 滞后2期 | 滞后3期 | 滞后4期 | 滞后5期 | |
社交媒体 | 0.20 | 1.79 | 2.33* | 2.33** | 2.18** |
新闻 | 1.33 | 1.68 | 2.32* | 1.71 | 1.56 |
注: 表中数值为格兰杰因果检验的 |
表10 基于月度情绪划分的投资组合 |
高 | 中 | 低 | 高 | 中 | 低 | ||
市值 | |||||||
小 | |||||||
( | ( | ( | ( | ( | ( | ||
中 | 0.484 | 0.274 | 0.209 | 1.716*** | |||
(0.87) | (0.47) | (0.38) | (3.62) | ( | ( | ||
大 | 1.004** | 0.767* | 0.679 | 1.920*** | 0.549 | ||
(2.400) | (1.79) | (1.64) | (4.88) | (1.31) | ( |
注: 括号中的数字为 |
表11 月度情绪因子对市场异象的解释能力 |
账面市值比 | 投资 | 盈利 | 动量 | 短期反转 | 长期反转 | |
社交媒体情绪因子 | 0.01 | 0.04 | 0.23 | |||
(0.50) | ( | (1.11) | ( | (1.64) | ( | |
新闻情绪因子 | 0.01 | 0.01 | 0.03 | |||
(0.41) | (0.28) | (0.64) | ( | ( | ( | |
控制FF5因子 | 是 | 是 | 是 | 是 | 是 | 是 |
注: 括号中的数字为 |
表12 月度情绪因子对波动率异象的解释能力 |
波动率 | 低 | 3 | 5 | 7 | 9 | 高 | 高-低 |
0.24 | 0.13 | ||||||
(1.26) | ( | (0.74) | ( | ( | ( | ( | |
新闻 | 0.01 | 0.19** | 0.19* | 0.47*** | 0.59*** | ||
( | ( | (0.17) | (2.09) | (1.80) | (3.40) | (3.56) | |
社交媒体 | 0.02 | 0.01 | |||||
(0.36) | ( | ( | (0.18) | ( | ( | ( | |
控制FF5因子 | 是 | 是 | 是 | 是 | 是 | 是 | 是 |
特质波动率 | 低 | 3 | 5 | 7 | 9 | 高 | 高-低 |
0.28* | 0.12 | ||||||
(1.81) | ( | (0.64) | ( | ( | ( | ( | |
新闻 | 0.21** | 0.25** | 0.37*** | 0.47*** | |||
( | ( | ( | (2.60) | (2.43) | (2.87) | (3.13) | |
社交媒体 | 0.04 | 0.01 | |||||
( | (0.93) | ( | ( | ( | ( | (0.06) | |
控制FF5因子 | 是 | 是 | 是 | 是 | 是 | 是 | 是 |
注: 括号中的数字为 |
韩立岩, 伍燕然, 投资者情绪与IPOs之谜——抑价或者溢价[J]. 管理世界, 2007, (3): 51- 61.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
何诚颖, 陈锐, 薛冰, 何牧原, 投资者情绪、有限套利与股价异象[J]. 经济研究, 2021, 56 (1): 58- 73.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
姜富伟, 孟令超, 唐国豪, 媒体文本情绪与股票回报预测[J]. 经济学(季刊), 2021, 21 (4): 1323- 1344.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
林建浩, 张一帆, 陈良源, 邓益萌, 基于新闻情绪的机器学习交易策略[J]. 计量经济学报, 2022, 2 (4): 881- 908.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
唐国豪, 姜富伟, 张定胜, 金融市场文本情绪研究进展[J]. 经济学动态, 2016, (11): 137- 147.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
汪昌云, 武佳薇, 媒体语气、投资者情绪与IPO定价[J]. 金融研究, 2015, (9): 174- 189.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
游家兴, 吴静, 沉默的螺旋: 媒体情绪与资产误定价[J]. 经济研究, 2012, 47 (7): 141- 152.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
张飞鹏, 徐一雄, 陈曦, 周勇, 基于新闻文本情绪的区间值股票回报预测研究[J]. 计量经济学报, 2024, 4 (1): 204- 230.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
张维, 李奕, 王鹏飞, 社交媒体与资本市场研究进展与展望: 基于文献计量的方法[J]. 计量经济学报, 2022, 2 (1): 32- 57.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
郑志刚, 丁冬, 汪昌云, 媒体的负面报道、经理人声誉与企业业绩改善——来自我国上市公司的证据[J]. 金融研究, 2011, (12): 163- 176.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Akyıldırım E, Altarovici A, Ekinci C, (2015). Effects of Firm-specific Public Announcements on Market Dynamics: Implications for High-frequency Traders[M]// Handbook of High Frequency Trading: 305.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Bochkay K, Dimitrov V, (2014). Qualitative Management Disclosures and Market Sentiment[R]. Working Paper.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
Lee E, (2013). Individual Stock Investor Sentiment, Stock Issuance, and Financial Market Anomalies[D]. Philadelphia: University of Pennsylvania.
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_citation.content}}
{{custom_citation.annotation}}
|
{{custom_ref.label}} |
{{custom_citation.content}}
{{custom_citation.annotation}}
|
/
〈 |
|
〉 |