Scholarlink

<p>This study investigated the sentiment of Twitter discourse on Open Educational Resources (OER). We collected 124,126 tweets containing hashtags related to OER posted from January 2017 to December 2021. We performed fine-grained sentiment analysis using Bidirectional Encoder Representations from Transformers (BERT) to categorize tweets into five sentiment classes: strongly negative, weakly negative, neutral, weakly positive and strongly positive. In addition, thematic analysis was performed by using PyTorch to identify the hidden themes in the tweets. Findings from this study reveal a predominantly positive sentiment toward OER on Twitter, highlighting the perceived benefits of accessibility, inclusivity, and the potential for enhancing educational equality. However, we also found that there are some negative sentiments expressed towards OER, with concerns about quality and effectiveness being the main reasons for criticism. In addition, longer tweets were more likely to express negative sentiments about OER. Finally, the thematic analysis revealed that most tweets center on resources or products that are obtainable through open licensing. These findings have implications for the promotion and implementation of OER and for understanding the role of social media in shaping discourse on education.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analyzing the discourse on open educational resources on Twitter: a sentiment analysis approach

  • 期刊论文

  • 发表日期：

    2025年2月10日

查看全文
  • Kaushal Kumar Bhagat,
  • Sanjaya Mishra,
  • Ashis Kumar Parida,
  • Alyal Samal,
  • Georgios Lampropoulos,
  • Alakh Dixit

摘要

This study investigated the sentiment of Twitter discourse on Open Educational Resources (OER). We collected 124,126 tweets containing hashtags related to OER posted from January 2017 to December 2021. We performed fine-grained sentiment analysis using Bidirectional Encoder Representations from Transformers (BERT) to categorize tweets into five sentiment classes: strongly negative, weakly negative, neutral, weakly positive and strongly positive. In addition, thematic analysis was performed by using PyTorch to identify the hidden themes in the tweets. Findings from this study reveal a predominantly positive sentiment toward OER on Twitter, highlighting the perceived benefits of accessibility, inclusivity, and the potential for enhancing educational equality. However, we also found that there are some negative sentiments expressed towards OER, with concerns about quality and effectiveness being the main reasons for criticism. In addition, longer tweets were more likely to express negative sentiments about OER. Finally, the thematic analysis revealed that most tweets center on resources or products that are obtainable through open licensing. These findings have implications for the promotion and implementation of OER and for understanding the role of social media in shaping discourse on education.