Toward an enriched understanding of factors influencing Filipino behavior during elections through the analysis of Twitter data

Pablo, Zelinna; Oco, Nathaniel; Roldan, Ma. Divina Gracia Z.; Cheng, Charibeth; Roxas, Rachel Edita

doi:10.1080/01154451.2014.964794

Cited by 10 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since LDA is an unsupervised text classification algorithm based on the "bag-of-words model" [38], it may sometimes misclassify documents or misidentify topics [39][40][41]; therefore, it is important to manually assess representative documents (in our case, Weibo posts). In this study, LDA outputs was verified and improved by 2 independent researchers (YS and QW) to analyze key words generated by the LDA model and manually review sample posts for each topic.…”

Section: Discussionmentioning

confidence: 99%

Comparison of Public Responses to Containment Measures During the Initial Outbreak and Resurgence of COVID-19 in China: Infodemiology Study (Preprint)

Zhou¹,

Song²,

Jiang³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND Monitoring public responses is crucial to inform policy measures to prepare for COVID-19 resurgence around the world. OBJECTIVE To assess and compare public responses towards containment measures during the initial outbreak and resurgence of COVID-19 epidemic in China. METHODS We collected all COVID-19 related posts from Sina Weibo (China’s Twitter) during the initial outbreak in China and resurgence in Beijing. With a Python script, we constructed subsets of Weibo posts focusing on three containment measures: lockdown, test-trace-isolate, and suspension of gatherings. Baidu’s open source sentiment analysis model, and Latent Dirichlet Allocation model, a widely-used machine learning algorithm, were used to assess public’s attention, sentiment, and frequently discussed topics on each containment measure. RESULTS During the initial outbreak, the amount of Weibo posts escalated dramatically following Wuhan lockdown, a high proportion of posts showed negative sentiment towards all three containment measures, and discrimination-related topics arose. Compared to the initial outbreak, the public expressed less attention and less negative sentiment on containment measures, and were more supportive towards containment measures during the COVID-19 resurgence. The public shifted their focus to the impacts of containment measures on their daily lives or work. CONCLUSIONS As China’s response strategy switched from lockdown to a targeted response in the COVID-19 resurgence, public responses became more rational. When COVID-19 resurges, more targeted test-trace-isolate strategies for high-risk population should be promoted to balance epidemic control and its impacts on daily lives and the economy.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of Public Responses to Containment Measures During the Initial Outbreak and Resurgence of COVID-19 in China: Infodemiology Study (Preprint)

Zhou¹,

Song²,

Jiang³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Since LDA is an unsupervised text classification algorithm based on the “bag-of-words model” [ 38 ], it may sometimes misclassify documents or misidentify topics [ 39 - 41 ]; therefore, it is important to manually assess representative documents (in our case, Weibo posts). In this study, LDA outputs was verified and improved by 2 independent researchers (YS and QW) to analyze key words generated by the LDA model and manually review sample posts for each topic.…”

Section: Methodsmentioning

confidence: 99%

Comparison of Public Responses to Containment Measures During the Initial Outbreak and Resurgence of COVID-19 in China: Infodemiology Study

Zhou¹,

Song²,

Jiang³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

Background COVID-19 cases resurged worldwide in the second half of 2020. Not much is known about the changes in public responses to containment measures from the initial outbreak to resurgence. Monitoring public responses is crucial to inform policy measures to prepare for COVID-19 resurgence. Objective This study aimed to assess and compare public responses to containment measures during the initial outbreak and resurgence of COVID-19 in China. Methods We curated all COVID-19–related posts from Sina Weibo (China’s version of Twitter) during the initial outbreak and resurgence of COVID-19 in Beijing, China. With a Python script, we constructed subsets of Weibo posts focusing on 3 containment measures: lockdown, the test-trace-isolate strategy, and suspension of gatherings. The Baidu open-source sentiment analysis model and latent Dirichlet allocation topic modeling, a widely used machine learning algorithm, were used to assess public engagement, sentiments, and frequently discussed topics on each containment measure. Results A total of 8,985,221 Weibo posts were curated. In China, the containment measures evolved from a complete lockdown for the general population during the initial outbreak to a more targeted response strategy for high-risk populations during COVID-19 resurgence. Between the initial outbreak and resurgence, the average daily proportion of Weibo posts with negative sentiments decreased from 57% to 47% for the lockdown, 56% to 51% for the test-trace-isolate strategy, and 55% to 48% for the suspension of gatherings. Among the top 3 frequently discussed topics on lockdown measures, discussions on containment measures accounted for approximately 32% in both periods, but those on the second-most frequently discussed topic shifted from the expression of negative emotions (11%) to its impacts on daily life or work (26%). The public expressed a high level of panic (21%) during the initial outbreak but almost no panic (1%) during resurgence. The more targeted test-trace-isolate measure received the most support (60%) among all 3 containment measures in the initial outbreak, and its support rate approached 90% during resurgence. Conclusions Compared to the initial outbreak, the public expressed less engagement and less negative sentiments on containment measures and were more supportive toward containment measures during resurgence. Targeted test-trace-isolate strategies were more acceptable to the public. Our results indicate that when COVID-19 resurges, more targeted test-trace-isolate strategies for high-risk populations should be promoted to balance pandemic control and its impact on daily life and the economy.

show abstract

“…We qualitatively analyze discourse in the form of text documents with the assistance of quantitative text mining procedures. In general, researchers have used text mining approaches when investigating Philippine political issues (see Cabling, Drago, & Andrei, 2017; Pablo, Oco, Roldan, Cheng, & Roxas, 2014; Soriano, Roldan, Cheng, & Oco, 2016). Similarly, the use of these methods to assist social constructionist qualitative analysis is a fast-emerging development (see Montiel, Boller, Uyheng, & Espina, 2019; Montiel, de la Paz, & Cerafica, 2019; Montiel, Dela Paz, & Custodio, 2017; Montiel & Uyheng, 2020) especially in the research of discourse (see Freake, Gentil, & Sheyholislami, 2011; Liu & Zhang, 2018; Montiel, Umel, & de Leon, 2016; Pérez, 2018; Taylor, 2014; Törnberg & Törnberg, 2016; Zhang & Mihelj, 2012).…”

Section: Case Of State Violence: Philippine Government’s Adomentioning

confidence: 99%

Legitimizing state violence: A comparative positioning analysis of discourses from the government and citizen supporters of the antidrug operations.

Camacho¹,

Montiel²

2021

Peace and Conflict: Journal of Peace Psychology

View full text Add to dashboard Cite

The present study proposes two distinct yet bidirectionally related forms of legitimation of state violence: those enacted by the government and those enacted by its citizens. We anchor this proposal upon a positioning framework. To demonstrate this conceptualization, we used a mixed methods approach that uses quantitative text mining procedures to supplement a qualitative positioning analysis. We analyzed a corpus of 18,968 words from presidential speeches to represent the government. At the same time, a corpus of 21,763 words from prodrug war Facebook comments to represent the citizens. We built and validated a classification model using support vector machines (SVM), which successfully distinguished between government and citizen utterances with an accuracy of 78.12%. Within the qualitative positioning analysis, we analyzed three storylines for the government and three storylines from the citizens. We show that bidirectional legitimation manifests between unique storylines of the government and citizens that share similar positionings. This study suggests that citizen discourse constructs state violence as acceptable on a different and yet equivalent level to the discourse of government politicians. We recommend for research in sociopolitical fields to shift in focus to comparatively analyze the unique discourses of both citizens and governments for episodes of national violence. Public Significance StatementMoving away from traditional dichotomies of the dominant and the dominated, the study becomes relevant through the introduction of an analytical framework and methodology for peace psychology that emphasizes an equal weight in the power of governments and citizens of a country. The study locates this equality in power within the capability of both governments and citizens to wield discourses in public spaces, with a particular focus on online spaces and social networking sites that are exponentially accessible venues for all forms of discussion. The study and its framework grant the general public the opportunity to scrutinize its specific contributions within online discussions of the political episodes of its nation; particularly the propagation and acceptance of state violence, which is a concept nominally tied to governments.

show abstract

Toward an enriched understanding of factors influencing Filipino behavior during elections through the analysis of Twitter data

Cited by 10 publications

References 13 publications

Comparison of Public Responses to Containment Measures During the Initial Outbreak and Resurgence of COVID-19 in China: Infodemiology Study (Preprint)

Comparison of Public Responses to Containment Measures During the Initial Outbreak and Resurgence of COVID-19 in China: Infodemiology Study (Preprint)

Comparison of Public Responses to Containment Measures During the Initial Outbreak and Resurgence of COVID-19 in China: Infodemiology Study

Legitimizing state violence: A comparative positioning analysis of discourses from the government and citizen supporters of the antidrug operations.

Contact Info

Product

Resources

About