A content analysis: analyzing topics of conversation under the #sustainability hashtag on Twitter

Author:

Gerber AydanORCID

Abstract

Abstract This study aimed to identify and understand the major topics of discussion under the #sustainability hashtag on Twitter (now known as “X”) and understand user engagement. The sharp increase in social media usage combined with a rise in climate anomalies in recent years makes the area of sustainability with respect to social media a critical topic. Python was used to gather Twitter posts between January 1, 2023, and March 1, 2023. User engagement metrics were analyzed using a variety of statistical analysis methods, including keyword-frequency analysis and Latent Dirichlet Allocation (LDA), which were used to identify significant topics of discussion under the #sustainability hashtag. Additionally, histograms and scatter plots were used to visualize user engagement. LDA analysis was conducted with 7 topics after trials were run with various topics and results were analyzed to determine which number of topics best fit the dataset. The frequency analysis provided a basic overview of the discourse surrounding #sustainability with the topics of technology, business and industry, environmental awareness, and discussion of the future. The LDA model provided a more comprehensive view, including additional topics such as Environmental, Social, and Governance (ESG) and infrastructure, investing, collaboration, and education. These findings have implications for researchers, businesses, organizations, and politicians seeking to align their strategies and actions with the major topics surrounding sustainability on Twitter to have a greater impact on their audience. Researchers can use the results of this study to guide further research on the topic or contextualize their study with existing literature within the field of sustainability.

Publisher

Cambridge University Press (CUP)

Reference20 articles.

1. Understanding #WorldEnvironmentDay User Opinions in Twitter: A Topic-Based Sentiment Analysis Approach

2. Termite

3. 15EkbergC (2022) Netflix-sentiment-analysis/710 final.ipynb at main · 15EkbergC/netflix-sentiment-analysis. GitHub. Available at https://github.com/15EkbergC/Netflix-Sentiment-Analysis/blob/main/710%20Final.ipynb (accessed 19 March 2023).

4. Kulshrestha, R (2020) Latent Dirichlet Allocation (LDA). Medium. Available at https://towardsdatascience.com/latent-dirichlet-allocation-lda-9d1cd064ffa2 (accessed 19 March 2023).

5. JustAnotherArchivist (2023) Justanotherarchivist/snscrape: A social networking service scraper in Python. GitHub. Available at https://github.com/JustAnotherArchivist/snscrape (accessed 19 March 2023).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3