The Ivory Tower Lost: How College Students Respond Differently than the General Public to the COVID-19 Pandemic

Duong, Viet; Pham, Phu; Yang, Tongyu; Wang, Yu; Luo, Jiebo

doi:10.48550/arxiv.2004.09968

Cited by 13 publications

(16 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Opinion mining is the computational treatment of opinions, sentiments, and subjectivity of text [28]. Sentiment classification techniques based on NLP and ML have been widely applied for opinion mining in di verse areas, including public health [79 ], movie reviews [27], airline service [67], political news [26], and the COVID-19 pandemi c [17,40 ]. Sentiment classification is a sub-discipline of text classification , which is concerned with classifying a text to a class for analyzing opinion or sentiment in texts.…”

Section: Related Opinion Mining Approachesmentioning

confidence: 99%

Public Sentiment toward Solar Energy—Opinion Mining of Twitter Using a Transformer-Based Language Model

et al. 2021

View full text Add to dashboard Cite

Public acceptance and support for renewable energy are important determinants of the low-carbon energy transition. This paper examines public sentiment toward solar energy in the United States using data from Twitter, a micro-blogging platform on which people post messages, known as tweets. We filtered tweets specific to solar energy and performed a classification task using Robustly optimized Bidirectional Encoder Representations from Transformers (RoBERTa). Our RoBERTa-based sentiment classification model, fine-tuned with 6300 manually annotated tweets specific to solar energy, attains 80.2% accuracy for ternary (positive, neutral, or negative) classification. Analyzing 266,686 tweets during the period of January to December 2020, we find public sentiment varies widely across states (Coefficient of Variation =164.66%). Within the study period, the Northeast U.S. region shows more positive sentiment toward solar energy than did the South U.S. region. Public opinion on solar energy is more positive in states with a larger share of Democratic voters in the 2020 presidential election. Public sentiment toward solar energy is more positive in states with consumer-friendly net metering policies and a more mature solar market. States that wish to gain public support for solar energy might want to consider implementing consumer-friendly net metering policies and support the growth of solar businesses.

show abstract

Section: Related Opinion Mining Approachesmentioning

confidence: 99%

Public Sentiment toward Solar Energy—Opinion Mining of Twitter Using a Transformer-Based Language Model

et al. 2021

View full text Add to dashboard Cite

show abstract

“…During the COVID-19 pandemic, instructors and education researchers developed various strategies combined with known remote learning practices with impromptu solutions to achieve learning goals and receive feedback. In a sentiment analysis study on college students during COVID-19, Duong et al [16] showed that 81.3% of college students showed dislikes for remote learning. Xu et al [57] found a strong decline in performance for males, beginner-level students, Black students, and students that were already under-performing when classes moved online.…”

Section: Effective Practices For Remote Learningmentioning

confidence: 99%

The Other Side of Black Screen: Rethinking Interaction in Synchronous Remote Learning for Collaborative Programming

Chowdhury¹

2021

Preprint

View full text Add to dashboard Cite

Collaborative learning environments such as programming labs are crucial for learning experiential hands-on skills such as critical thinking and problem solving, and peer discussion. In a traditional laboratory setting, many of these skills can be practiced through natural interaction (verbal, facial) and physical co-location. However, during and after a global pandemic, these learning practices cannot be exercised safely in in-person settings any longer and thus need to be re-imagined for a remote learning environment. As discussions spur about effective remote learning practices, there is an urgency for identifying the unique needs demanded by both students and instructors under different learning environments. How can we design remote learning to offer broadly accessible learning, by drawing in-person practices and combining them with the power of remote learning solutions? In this case study, we present observations of in-person and online versions of 2 introductory programming courses offered before and during the COVID-19 pandemic. Our observations reveal certain user needs and interaction practices under 5 themes that are unique to students' prior experience with the curriculum and academic level. We find that the current online video-conferencing platforms cannot foster collaborative learning among peers, lacks learning ambiance and spontaneous engagement between students and instructors. Based on our findings, we propose design recommendations and intervention strategies to improve current practices in synchronous remote learning that can facilitate a better learning environment, particularly for introductory lab courses.CCS Concepts: • Human-centered computing → Empirical studies in collaborative and social computing; • Social and professional topics → Computing education.

show abstract

“…Themes of previous studies that focus on exploration of, description of, correlation of, or predictive modeling with Twitter data during COVID-19 pandemic include sentiment analysis [17], [25], [26], [27], [28], public attitude/interest measurement [21], [29], [30], [31], content analysis [32], [33], [15], [34], [35], [36], topic modeling [37], [16], [38], [39], [40], [26], [27], analysis of misinformation, disinformation, or conspiracies [41], [20], [42], [43], [44], [45], [46], outbreak detection or disease nowcasting/forecasting [19], [18], and more [47], [48], [49], [50], [51], [52]. Similarly, data from other social media channels (e.g.…”

Section: Going Beyond Correlationsmentioning

confidence: 99%

Causal Modeling of Twitter Activity During COVID-19

Gencoglu,

Gruber

2020

Preprint

View full text Add to dashboard Cite

Understanding the characteristics of public attention and perception is an essential prerequisite for appropriate crisis management during adverse health events. This is even more crucial during a pandemic such as COVID-19, as primary responsibility of risk management is not centralized to a single institution, but distributed across society. While numerous studies utilize Twitter data in descriptive or predictive context during COVID-19 pandemic, causal modeling of public attention has not been investigated. In this study, we propose a causal inference approach to discover and quantify causal relationships between pandemic characteristics (e.g. number of infections and deaths) and Twitter activity as well as public sentiment. Our results show that the proposed method can successfully capture the epidemiological domain knowledge and identify variables that affect public attention and perception. We believe our work contributes to the field of infodemiology by distinguishing events that correlate with public attention from events that cause public attention.

show abstract

The Ivory Tower Lost: How College Students Respond Differently than the General Public to the COVID-19 Pandemic

Cited by 13 publications

References 24 publications

Public Sentiment toward Solar Energy—Opinion Mining of Twitter Using a Transformer-Based Language Model

Public Sentiment toward Solar Energy—Opinion Mining of Twitter Using a Transformer-Based Language Model

The Other Side of Black Screen: Rethinking Interaction in Synchronous Remote Learning for Collaborative Programming

Causal Modeling of Twitter Activity During COVID-19

Contact Info

Product

Resources

About