Linguistic Patterns in Pandemic-Related Content: A Comparative Analysis of COVID-19, Constraint, and Monkeypox Datasets_Reproducibility Guide & Python code
Fuente:
Zenodo
Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902087005110272 |
|---|---|
| author | SIKOSANA, Mkululi |
| author_facet | SIKOSANA, Mkululi |
| contents | <p>This archive contains a Python script and a detailed reproducibility guide for analyzing linguistic patterns in pandemic-related social media content. The analysis covers three datasets: COVID-19 false narratives (FNR), CONSTRAINT 2021, and Monkeypox tweets.</p> <p>The <code>combined_analysis_script.py</code> is the core component. It automates a multi-step pipeline that includes:</p> <ul> <li> <p><strong>Preprocessing:</strong> Cleaning raw text by removing URLs, HTML tags, hashtags, and mentions, and filtering out very short posts.</p> </li> <li> <p><strong>Linguistic Metric Computation:</strong> Calculating readability scores (Flesch Reading Ease and Flesch-Kincaid Grade Level), and normalizing counts of rhetorical markers (exclamation and question marks) and persuasive words.</p> </li> <li> <p><strong>Statistical Analysis:</strong> Running descriptive statistics and non-parametric tests like the Kruskal-Wallis H-test to compare linguistic features across the three datasets.</p> </li> <li> <p><strong>Visualization:</strong> Generating boxplots and bar charts to visualize the distributions of the calculated metrics.</p> </li> <li> <p><strong>Logistic Regression:</strong> A model that demonstrates how linguistic features (e.g., persuasive language) might predict a post's engagement level, though it's presented as an illustrative example rather than a definitive predictor.</p> </li> </ul> <p><span>The accompanying </span></p> <p><code><span>Reproducibility Guide.pdf</span></code><span> provides detailed, step-by-step instructions for a user to replicate the study's findings<sup></sup></span>. It outlines how to:</p> <ol> <li><span>Acquire the three necessary datasets<sup></sup></span>.</li> <li><span>Set up the required Python environment with all dependencies<sup></sup></span>.</li> <li><span>Run the analysis script from the command line, explaining the command-line arguments and expected outputs<sup></sup></span>.</li> <li><span>Interpret the results within a psychological framework, specifically the Elaboration Likelihood Model of persuasion</span></li> </ol> <p><span>The guide also includes an ethical section, advising users not to redistribute the raw social media data and to respect user privacy<sup></sup></span>. <span>The overall purpose is to provide a complete, transparent, and reproducible workflow for other researchers to verify the study's conclusions and apply the methodology to new datasets<sup></sup></span>.</p> <p></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17024569 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Linguistic Patterns in Pandemic-Related Content: A Comparative Analysis of COVID-19, Constraint, and Monkeypox Datasets_Reproducibility Guide & Python code SIKOSANA, Mkululi misinformation, infodemic, COVID-19, Monkeypox, social media, linguistic analysis, reproducibility, reproducible research, text mining, natural language processing (NLP), computational social science <p>This archive contains a Python script and a detailed reproducibility guide for analyzing linguistic patterns in pandemic-related social media content. The analysis covers three datasets: COVID-19 false narratives (FNR), CONSTRAINT 2021, and Monkeypox tweets.</p> <p>The <code>combined_analysis_script.py</code> is the core component. It automates a multi-step pipeline that includes:</p> <ul> <li> <p><strong>Preprocessing:</strong> Cleaning raw text by removing URLs, HTML tags, hashtags, and mentions, and filtering out very short posts.</p> </li> <li> <p><strong>Linguistic Metric Computation:</strong> Calculating readability scores (Flesch Reading Ease and Flesch-Kincaid Grade Level), and normalizing counts of rhetorical markers (exclamation and question marks) and persuasive words.</p> </li> <li> <p><strong>Statistical Analysis:</strong> Running descriptive statistics and non-parametric tests like the Kruskal-Wallis H-test to compare linguistic features across the three datasets.</p> </li> <li> <p><strong>Visualization:</strong> Generating boxplots and bar charts to visualize the distributions of the calculated metrics.</p> </li> <li> <p><strong>Logistic Regression:</strong> A model that demonstrates how linguistic features (e.g., persuasive language) might predict a post's engagement level, though it's presented as an illustrative example rather than a definitive predictor.</p> </li> </ul> <p><span>The accompanying </span></p> <p><code><span>Reproducibility Guide.pdf</span></code><span> provides detailed, step-by-step instructions for a user to replicate the study's findings<sup></sup></span>. It outlines how to:</p> <ol> <li><span>Acquire the three necessary datasets<sup></sup></span>.</li> <li><span>Set up the required Python environment with all dependencies<sup></sup></span>.</li> <li><span>Run the analysis script from the command line, explaining the command-line arguments and expected outputs<sup></sup></span>.</li> <li><span>Interpret the results within a psychological framework, specifically the Elaboration Likelihood Model of persuasion</span></li> </ol> <p><span>The guide also includes an ethical section, advising users not to redistribute the raw social media data and to respect user privacy<sup></sup></span>. <span>The overall purpose is to provide a complete, transparent, and reproducible workflow for other researchers to verify the study's conclusions and apply the methodology to new datasets<sup></sup></span>.</p> <p></p> |
| title | Linguistic Patterns in Pandemic-Related Content: A Comparative Analysis of COVID-19, Constraint, and Monkeypox Datasets_Reproducibility Guide & Python code |
| topic | misinformation, infodemic, COVID-19, Monkeypox, social media, linguistic analysis, reproducibility, reproducible research, text mining, natural language processing (NLP), computational social science |
| url | https://doi.org/10.5281/zenodo.17024569 |