Microblog Rumor Detection Based
on Comment Sentiment and CNN-LSTM
Sheng Lv, Haijun Zhang
(&)
, Han He, and Bingcai Chen
School of Computer Science and Technology, Xinjiang Normal University,
Urumqi 830054, China
zhjlp@163.com
Abstract. Traditional rumor detection methods, such as feature engineering,
are difficult and time-consuming. Moreover, the user page structure of Sina
Weibo includes not only the content text, but also a large amount of comment
information, among which the sentimental characteristics of comment are difficult to learn by neural network. In order to solve these problems, a rumor
detection method based on comment sentiment and CNN-LSTM is proposed,
and long short-term memory (LSTM) is connected to the pooling layer and full
connection layer of convolutional neural network (CNN). Meanwhile, comment
sentiment is added to rumor detection model as an important feature. The
effectiveness of this method is verified by experiments.
Keywords: Sentimental analysis Á Deep learning Á Rumor detection Á Word
vector
1 Introduction
With the rise of social networks, Sina Weibo has become the largest social network
information platform in China. According to the third quarter of Sina Weibo 2017, the
monthly active users exceed 376 million, the daily active users exceed 165 million, and
hundreds of millions of microblogs are published every day. According to China’s new
media development report, 60% of Internet rumors first appeared in Sina Weibo
platforms, which has become the largest media for the dissemination of false information. Sina Weibo provides information services such as publishing, sharing, and
learning, and users can get and share information only by moving their fingers.
Therefore, the harm and impact of Sina Weibo rumors are even greater. Rumor
detection can serve the task of rumor clearance, such as prevention and supervision, but
at present, we still rely on manual reporting to dispel rumors. How to extract rumor
features and design an effective rumor detection method become more and more
significant.
This paper proposes a rumor detection method based on comment sentiment and
CNN-LSTM. The remainder of this paper is arranged as follows: The second section
introduces the related work of rumor detection. In the third section, the rumor detection
method based on comment sentiment and CNN-LSTM is introduced. The fourth part
gives experiments and discussions. Finally, the conclusions and future works are
presented.
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 148–156, 2020.
https://doi.org/10.1007/978-981-15-0187-6_17
on Comment Sentiment and CNN-LSTM
Sheng Lv, Haijun Zhang
(&)
, Han He, and Bingcai Chen
School of Computer Science and Technology, Xinjiang Normal University,
Urumqi 830054, China
zhjlp@163.com
Abstract. Traditional rumor detection methods, such as feature engineering,
are difficult and time-consuming. Moreover, the user page structure of Sina
Weibo includes not only the content text, but also a large amount of comment
information, among which the sentimental characteristics of comment are difficult to learn by neural network. In order to solve these problems, a rumor
detection method based on comment sentiment and CNN-LSTM is proposed,
and long short-term memory (LSTM) is connected to the pooling layer and full
connection layer of convolutional neural network (CNN). Meanwhile, comment
sentiment is added to rumor detection model as an important feature. The
effectiveness of this method is verified by experiments.
Keywords: Sentimental analysis Á Deep learning Á Rumor detection Á Word
vector
1 Introduction
With the rise of social networks, Sina Weibo has become the largest social network
information platform in China. According to the third quarter of Sina Weibo 2017, the
monthly active users exceed 376 million, the daily active users exceed 165 million, and
hundreds of millions of microblogs are published every day. According to China’s new
media development report, 60% of Internet rumors first appeared in Sina Weibo
platforms, which has become the largest media for the dissemination of false information. Sina Weibo provides information services such as publishing, sharing, and
learning, and users can get and share information only by moving their fingers.
Therefore, the harm and impact of Sina Weibo rumors are even greater. Rumor
detection can serve the task of rumor clearance, such as prevention and supervision, but
at present, we still rely on manual reporting to dispel rumors. How to extract rumor
features and design an effective rumor detection method become more and more
significant.
This paper proposes a rumor detection method based on comment sentiment and
CNN-LSTM. The remainder of this paper is arranged as follows: The second section
introduces the related work of rumor detection. In the third section, the rumor detection
method based on comment sentiment and CNN-LSTM is introduced. The fourth part
gives experiments and discussions. Finally, the conclusions and future works are
presented.
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 148–156, 2020.
https://doi.org/10.1007/978-981-15-0187-6_17