https://github.com/karm-patel/samachar-news-media-on-air-pollution

This repository contains codes (Jupyter Notebooks) to reproduce the figures and results of our submission accepted in COMPASS 2022.
https://github.com/karm-patel/samachar-news-media-on-air-pollution

airpollution newsarticles python topic-modeling

Last synced: 27 days ago
JSON representation

This repository contains codes (Jupyter Notebooks) to reproduce the figures and results of our submission accepted in COMPASS 2022.

• Host: GitHub
• URL: https://github.com/karm-patel/samachar-news-media-on-air-pollution
• Owner: karm-patel
• Created: 2021-10-26T15:16:00.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2022-08-11T15:26:44.000Z (about 3 years ago)
• Last Synced: 2025-04-02T10:43:36.767Z (7 months ago)
• Topics: airpollution, newsarticles, python, topic-modeling
• Language: HTML
• Homepage:
• Size: 64.3 MB
• Stars: 4
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# 

## Samachar: News Media on Air Pollution in India

This repository contains codes (Jupyter Notebooks) to reproduce the figures and results of our submission (https://dl.acm.org/doi/pdf/10.1145/3530190.3534812) accepted in [COMPASS 2022](https://compass.acm.org/). Each folder represents a section in the paper. 


- **Section Overview**

|**Section**|**Title**|**Decription**|

|--|--|--|

|3|[Dataset](dataset)|We are making the News-articles-dataset public. (**Note**:  PM25 data is publicly available in [CPCB](https://app.cpcbccr.com/ccr/#/caaqm-dashboard-all/caaqm-landing/caaqm-data-availability) portal and [OpenAQ](https://openaq.org/#/) website.)|

|5.1|[Research-Question-1](Research_Question_1)|Does the news media coverage around air pollution exhibit a geographical and/or temporal bias?|

|5.2|[Research-Question-2](Research_Question_2)|Does the news media coverage around air pollution exhibit deviation from scientific evidence around sources and impact of air pollution?|




- **Tables/Figures**

|Figure/Table|File/Folder| Decription |

|--|--|--|

|Figure 1 |[dataset/Figure-1_Number-of-cities-for-pm25-data-available.ipynb](dataset/Figure-1_Number-of-cities-for-pm25-data-available.ipynb)|To plot number of cities along with time for which PM25 data is available.|

|Figure 2|[dataset/Figure-2_TOI-vs-Hindu-articles_over_time.ipynb](dataset/Figure-2_TOI-vs-Hindu-articles_over_time.ipynb)|To plot articles of TOI and The Hindu over time (2010-21).|

|Figure 3 |[Research_Question_1/Figure-3_Choropleth_map_PM25_and_articles.ipynb](Research_Question_1/Figure-3_Choropleth_map_PM25_and_articles.ipynb)|Python Notebook to generate Choropleth map of India showing PM2.5 level and number of news articles|

|Figure 4|[Research_Question_1/Figure-4_Violation_of_India_limit_by_IGP.ipynb](Research_Question_1/Figure-4_Violation_of_India_limit_by_IGP.ipynb)|Time series of PM2.5 level and Number of articles for Delhi|

|Figure 5|[Research_Question_1/Figure-5_timeseries_of_aq_articles_delhi.ipynb](Research_Question_1/Figure-5_timeseries_of_aq_articles_delhi.ipynb)|Time series of PM2.5 level and Number of articles for Delhi|

|Table 3|[Research_Question_1/Table-3,4_pollution-in-IG-Plain_and_Delhi-time-series.ipynb](Research_Question_1/Table-3,4_pollution-in-IG-Plain_and_Delhi-time-series.ipynb)|PM2.5 and articles of Cities of Indo Gangetic (IG) plain|

|Table 4|[Research_Question_1/Table-3,4_pollution-in-IG-Plain_and_Delhi-time-series.ipynb](Research_Question_1/Table-3,4_pollution-in-IG-Plain_and_Delhi-time-series.ipynb)|PM2.5 and articles of 10 most highlighted cities in News-media|

|Figure 6 |[Research_Question_2/Figure-6_Topic-Modeling-tarining-LDA-model.ipynb](Research_Question_2/Figure-6_Topic-Modeling-tarining-LDA-model.ipynb)|Train LDA Topic modeling model using `gensim` and create visualization [LDA_topic_modelling_Visualization.html](https://karm-patel.github.io/Samachar-News-media-on-air-pollution/Research_Question_2/LDA_Visualization/LDA_topic_modelling_Visualization.html) using pyLDAvis.|

|Figure 7|[Research_Question_2/Figure-7_Topic-evolution-over-time.ipynb](Research_Question_2/Figure-7_Topic-evolution-over-time.ipynb)|Frequency of articles of topic over time |

|Figure 8|[Research_Question_2/Figure-8_Open-fire-vs-Stubble-burning-articles.ipynb](Research_Question_2/Figure-8_Open-fire-vs-Stubble-burning-articles.ipynb)|Timeseries of NASA Open Fire cout data (VIIRS) [`firedata`](Research_Question_2/firedata) to identify when stubble burning is happening and compare firecount|

|Figure 9|[Research_Question_2/Figure-9_Source-contribution-Delhi.ipynb](Research_Question_2/Figure-9_Source-contribution-Delhi.ipynb)|Comparison of Sources contribution to PM2.5 in Delhi and articles relavent to particular sources, to verify if media discussion is in consonance with source contribution.|

-  **Citation**

```sh

@inproceedings{patel2022samachar,

  title={Samachar: print news media on air pollution in India},

  author={Patel, Karm and Adhikary, Rishiraj and Patel, Zeel B and Batra, Nipun and Guttikunda, Sarath},

  booktitle={ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS)},

  pages={401--413},

  year={2022}

}

```