CASM: A Deep-Learning Approach for Identifying Collective Action Events with Text and Image Data from Social Media

Zhang, Han; Pan, Jennifer

doi:10.1177/0081175019860244

Cited by 134 publications

(108 citation statements)

References 97 publications

(97 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, the term "epidemic" is used by both Weibo-COV and Weiboscope to collect data, but in some posts "epidemic" refers to other outbreaks, such as the pneumonic plague. As the number of keywords expands, recall will increase but precision will decrease (Zhang and Pan, 2019), and that is what we observe: Weibo-COV contains more false positives than Weiboscope since Weibo-COV uses a substantially higher number of keywords. This is why it is crucial for the validity of our findings that we apply our machine learning classifier to identify COVID-related posts.…”

Section: Resultssupporting

confidence: 66%

“…Doing so can have substantive payoffs. For example, scholars of Chinese politics have noted a seeming disconnect between surveys showing high levels of political trust in China and analyses of Chinese social media data showing high frequencies of protest and discontent (Cai, 2010;Chen, 2012;Heurlin, 2020;King et al, 2013;Zhang and Pan, 2019). However, survey-based designs often, by default, incorporate both positive and negative sentiments.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Public Sentiment on Chinese Social Media during the Emergence of COVID19

Pan

2021

JQD

Self Cite

View full text Add to dashboard Cite

When COVID-19 first emerged in China, there was speculation that the outbreak would trigger public anger and weaken the Chinese regime. By analyzing millions of social media posts from Sina Weibo made between December 2019 and February 2020, we describe the contours of public, online discussions pertaining to COVID-19 in China. We find that discussions of COVID-19 became widespread on January 20, 2020, consisting primarily of personal reflections, opinions, updates, and appeals. We find that the largest bursts of discussion, which contain simultaneous spikes of criticism and support targeting the Chinese government, coincide with the January 23 lockdown of Wuhan and the February 7 death of Dr. Li Wenliang. Criticisms are directed at the government for perceived lack of action, incompetence, and wrongdoing—in particular, censoring information relevant to public welfare. Support is directed at the government for aggressive action and positive outcomes. As the crisis unfolds, the same events are interpreted differently by different people, with those who criticize focusing on the government’s shortcomings and those who praise focusing on the government’s actions.

show abstract

Section: Resultssupporting

confidence: 66%

Section: Discussionmentioning

confidence: 99%

Public Sentiment on Chinese Social Media during the Emergence of COVID19

Pan

2021

JQD

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is testable in 26 markets, and the entry pattern in 22 markets is as predicted. 17 Under random entry, the probability of such an outcome is 2 in 10,000.…”

Section: B Sequence Of Newspaper Entrymentioning

confidence: 99%

Media Bias in China

Qin¹,

Strömberg

Wu³

2018

American Economic Review

152

View full text Add to dashboard Cite

This paper examines whether and how market competition affected the political bias of government-owned newspapers in China from 1981 to 2011. We measure media bias based on coverage of government mouthpiece content ( propaganda) relative to commercial content. We first find that a reform that forced newspaper exits (reduced competition) affected media bias by increasing product specialization, with some papers focusing on propaganda and others on commercial content. Second, lower-level governments produce less-biased content and launch commercial newspapers earlier, eroding higher-level governments’ political goals. Third, bottom-up competition intensifies the politico-economic trade-off, leading to product proliferation and less audience exposure to propaganda. (JEL D72, L31, L82, O14, O17, P26, P31)

show abstract

“…Likewise, the social media data that has contributed the largest part of the events in this study have emerged as the source with by far the largest coverage of events and the fewest relative biases in data from China. 55 Censorship introduces another layer of potential bias. The following attributes of the data, however, minimize this effect.…”

Section: Data Validitymentioning

confidence: 99%

Defending Stability under Threat: Sensitive Periods and the Repression of Protest in Urban China

Steinhardt

2020

Journal of Contemporary China

View full text Add to dashboard Cite

How does the elevated threat of protests during sensitive periods affect state repression in a high-capacity authoritarian regime? Drawing on a dataset of over 3,100 protests in three Chinese megacities, this study provides three key findings: first, the frequency of protests before and during national-level focal events and subsequent to national-level disruptive events is depressed, suggesting preemptive repression is taking place. Second, the likelihood of responsive repression is marginally reduced before and during local-level focal events and slightly elevated after national-level disruptive events. Third, contention is intensified when local political elites meet. Sensitive periods do not bring contention to a standstill and costly bursts of responsive repression were not observed. Stability maintenance during times of increased regime-vulnerability was thus less rigid than often assumed. On 2 June, 2014, urban management officers in Shanghai's Pudong District forcefully removed an elderly woman's street vendor stall. They then manhandled two students who recorded the scene on camera. Quickly, a crowd of over 1,000 people gathered and blocked the officers and arriving police from leaving. An hour-long standoff ensued until a large police reinforcement managed to disperse the crowd. No major clashes or arrests were reported. 1 Two days later, on 4 June, a group of 46 petitioners took the metro from a suburb to the city center. They first traveled to the Shanghai Higher People's Court, where a security guard received their petition in support of their longstanding attempt to file an administrative litigation case against the city government. 2 After taking a group picture with a protest banner in front of the court, the petitioners had lunch and continued to the Shanghai People's Congress, where they delivered their complaint letter to a member of staff. No police presence or arrests were reported during their contentious city tour. 3 Although different in many ways, both 'contentious gatherings' 4 were triggered by alleged state misconduct and proceeded without massive repression, or even any coercion at all. This is remarkable because they occurred on or shortly before 4 June, the annual anniversary of the violent suppression of the Beijing student movement of 1989. The period preceding this anniversary undoubtedly is among the most 'sensitive periods' (敏感时期) on the Chinese political calendar, when the security apparatus is on high alert. The two episodes suggest that this does not necessarily lead to a total standstill of protests, or that those who do mobilize must expect punitive repression. While selective toleration is

show abstract

CASM: A Deep-Learning Approach for Identifying Collective Action Events with Text and Image Data from Social Media

Cited by 134 publications

References 97 publications

Public Sentiment on Chinese Social Media during the Emergence of COVID19

Public Sentiment on Chinese Social Media during the Emergence of COVID19

Media Bias in China

Defending Stability under Threat: Sensitive Periods and the Repression of Protest in Urban China

Contact Info

Product

Resources

About