Exploring Public Reaction to Air Quality on Social Media: The 2022 Saharan Dust Episode in Lisbon
Abstract
This study analyses the relationship between air quality and sentiments expressed on social media, focusing on the Saharan dust episode that affected Lisbon in March 2022. Environmental data were collected alongside geolocated Twitter posts (now rebranded as X) from the Lisbon area. The content of these posts was analysed using the Valence Aware Dictionary and sEntiment Reasoner algorithm to identify emotional patterns and assess correlations with fluctuations in atmospheric pollutants. A predictive analysis was also conducted using Decision Tree and Random Forest machine learning algorithms. The findings suggest that despite high levels of inhalable particulate matter (PM10) during the event, there was no significant change in online sentiments, which remained mostly neutral or slightly positive. This implies that the publics environ-mental perception may not be clearly reflected on social media, possibly due to cultural factors or the limited influence of Twitter in Portugal. The study concludes that integrating environmental and social data is feasible and valuable, but further research is needed to explore longer periods, other cities, and more advanced techniques, thus contributing to the understanding of air pollution and public perception in Portugal.References
[1] B. Ye, P. Krishnan, and S. Jia, “Public Concern about Air Pollution and Related Health Outcomes on Social Media in China: An Analysis of Data from Sina Weibo (Chinese Twitter) and Air Monitoring Stations,” Int. J. Environ. Res. Public Health, vol. 19, no. 23, Dec. 2022, doi: 10.3390/IJERPH192316115.
[2] D. Amangeldi, A. Usmanova, and P. Shamoi, “Understanding Environmental Posts: Sentiment and Emotion Analysis of Social Media Data,” IEEE Access, vol. 12, pp. 33504–33523, Jan. 2024, doi: 10.1109/ACCESS.2024.3371585.
[3] K. Wadhwa, D. Mehra, H. Gosain, and A. K. Haritash, “Sentiment Analysis of Air Quality Perception in Major Metro Cities of India,” 2023 14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023, p. Delhi, doi: 10.1109/ICCCNT56998.2023.10307448.
[4] G. Marques, I. M. Pires, N. Miranda, and R. Pitarma, “Air quality monitoring using assistive robots for ambient assisted living and enhanced living environments through internet of things,” Electronics (Switzerland), vol. 8, no. 12, p. 1375, Dec. 2019, doi: 10.3390/electronics8121375.
[5] T. Carpi, A. Hino, S. M. Iacus, and G. Porro, “The Impact of COVID-19 on Subjective Well-Being: Evidence from Twitter Data,” Journal of Data Science, vol. 21, no. 4, pp. 761–780, Oct. 2023, doi: 10.6339/22-JDS1066.
[6] S. Zheng, J. Wang, C. Sun, X. Zhang, and M. E. Kahn, “Air pollution lowers Chinese urbanites’ expressed happiness on social media,” Nat. Hum. Behav., vol. 3, no. 3, pp. 237–243, Mar. 2019, doi: 10.1038/s41562-018-0521-2.
[7] S. Shan, X. Ju, Y. Wei, and Z. Wang, “Effects of pm2.5 on people’s emotion: A case study of weibo (chinese twitter) in beijing,” Int. J. Environ. Res. Public Health, vol. 18, no. 10, May 2021, doi: 10.3390/IJERPH18105422.
[8] A. Liaw and M. Wiener, “Classification and Regression by randomForest,” vol. 2, no. 3, 2002, Accessed: Nov. 05, 2025. [Online]. Available: http://www.stat.berkeley.edu/
[9] Y. Tao, F. Zhang, C. Shi, and Y. Chen, “Social media data-based sentiment analysis of tourists’ air quality perceptions,” Sustainability (Switzerland), vol. 11, no. 18, p. 5070, Sep. 2019, doi: 10.3390/su11185070.
[10] Y. E. García et al., “Wildfires and social media discourse: exploring mental health and emotional wellbeing through Twitter,” Front. Public Health, vol. 12, 2024, doi: 10.3389/FPUBH.2024.1349609.
[11] B. Wang, N. Wang, and Z. Chen, “Research on air quality forecast based on web text sentiment analysis,” Ecol. Inform., vol. 64, Sep. 2021, doi: 10.1016/J.ECOINF.2021.101354.
[12] W. Zhai and C. Cheng, “A long short-term memory approach to predicting air quality based on social media data,” Atmos. Environ., vol. 237, Sep. 2020, doi: 10.1016/J.ATMOSENV.2020.117411.
[13] J. Min, H. Yunxiu, S. Yong, J. Fengxiang, and L. Ting, “Research on Analysis of Evaluation Influence Factors of Air Quality Opinions Sentiment Value and Quantification Method,” Water Air Soil Pollut., vol. 232, no. 7, p. 256, Jul. 2021, doi: 10.1007/s11270-021-05197-x.
[14] H. Ji et al., “Research on adaption to air pollution in Chinese cities: Evidence from social media-based health sensing,” Environ. Res., vol. 210, p. 112762, Jul. 2022, doi: 10.1016/j.envres.2022.112762.
[15] J. M. Postma et al., “Assessing community response to wildfire smoke: A multimethod study using social media,” Public Health Nurs., vol. 40, no. 1, pp. 153–162, Feb. 2023, doi: 10.1111/phn.13140.
[16] G. Yang, Y. Ju, and W. Ni, “Does the air pollution level information matter in public perception? Insights from China,” J. Environ. Manage., vol. 349, p. 119582, Jan. 2024, doi: 10.1016/J.JENVMAN.2023.119582.
[17] C. E. Slavik, D. A. Chapman, A. S. Cohen, N. Bendefaa, and E. Peters, “Clearing the air: evaluating institutions’ social media health messaging on wildfire and smoke risks in the US Pacific Northwest,” BMC Public Health, vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12889-024-17907-1.
[18] M. T. Marfori et al., “Public Health Messaging During Extreme Smoke Events: Are We Hitting the Mark?,” Front. Public Health, vol. 8, Sep. 2020, doi: 10.3389/FPUBH.2020.00465.
[19] W. Hong, Y. Wei, and S. Wang, “Left behind in perception of air pollution? A hidden form of spatial injustice in China,” Environment and Planning C: Politics and Space, vol. 40, no. 3, pp. 666–684, May 2022, doi: 10.1177/23996544211036145/ASSET/FDB83BA2-7C31-4935-88EF-99653086DD9C/ASSETS/IMAGES/LARGE/10.1177_23996544211036145-FIG1.JPG.
[20] L. Yan, F. Duarte, De Wang, S. Zheng, and C. Ratti, “Exploring the effect of air pollution on social activity in China using geotagged social media check-in data,” Cities, vol. 91, pp. 116–125, Aug. 2019, doi: 10.1016/J.CITIES.2018.11.011.
[21] C. Zhang and G. Zhang, “How Does Air Pollution Impact Residence Intention of Rural Migrants? Empirical Evidence from the CMDS,” Sustainability 2024, Vol. 16, Page 5784, vol. 16, no. 13, p. 5784, Jul. 2024, doi: 10.3390/SU16135784.
[22] P. Brimblecombe and Y. Lai, “Effect of fireworks, Chinese new year and the COVID-19 lockdown on air pollution and public attitudes,” Aerosol Air Qual. Res., vol. 20, no. 11, pp. 2318–2331, Nov. 2020, doi: 10.4209/AAQR.2020.06.0299.
[23] M. Burke et al., “Exposures and behavioural responses to wildfire smoke,” Nat. Hum. Behav., vol. 6, no. 10, pp. 1351–1361, Oct. 2022, doi: 10.1038/S41562-022-01396-6.
[24] H. O’Leary, S. Parr, and M. M. H. El-Sayed, “The breathing human infrastructure: Integrating air quality, traffic, and social media indicators,” Science of the Total Environment, vol. 827, Jun. 2022, doi: 10.1016/J.SCITOTENV.2022.154209.
[25] Y. Sun, F. Jin, Y. Zheng, M. Ji, and H. Wang, “A new indicator to assess public perception of air pollution based on complaint data,” Applied Sciences (Switzerland), vol. 11, no. 4, pp. 1–18, Feb. 2021, doi: 10.3390/APP11041894.
[26] M. Ashayeri, “Decoding Global Indoor Health Perception on Social Media Through NLP and Transformer Deep Learning,” in Artificial Intelligence in Performance-Driven Design: Theories, Methods, and Tools, wiley, 2024, pp. 159–185. doi: 10.1002/9781394172092.ch8.
[27] A. Madjar, I. Gjorshoska, J. Prodanova, A. Dedinec, and L. Kocarev, “Western Balkan societies’ awareness of air pollution. Estimations using natural language processing techniques,” Ecol. Inform., vol. 75, p. 102097, Jul. 2023, doi: 10.1016/j.ecoinf.2023.102097.
[28] R. Yu, C. Zeng, M. Chang, C. Bao, M. Tang, and F. Xiong, “Effects of Urban Vibrancy on an Urban Eco-Environment: Case Study on Wuhan City,” Int. J. Environ. Res. Public Health, vol. 19, no. 6, p. 3200, Mar. 2022, doi: 10.3390/ijerph19063200.
[29] S. Gurajala, S. Dhaniyala, and J. N. Matthews, “Understanding Public Response to Air Quality Using Tweet Analysis,” Social Media and Society, vol. 5, no. 3, Jul. 2019, doi: 10.1177/2056305119867656.
[30] Y. Yang, K. Y. Goh, H. H. Teo, and S. S. L. Tan, “The Impact of Air Pollution Information on Individuals’ Exercise Behavior: Empirical Study Using Wearable and Mobile Devices Data,” JMIR Mhealth Uhealth, vol. 12, p. e55207, Jan. 2024, doi: 10.2196/55207.
[31] H. O’Leary, D. Smiles, S. Parr, and M. M. H. El-Sayed, “‘I Can’t Breathe:’ The Invisible Slow Violence of Breathing Politics in Minneapolis,” Soc. Nat. Resour., vol. 36, no. 9, pp. 1098–1118, 2023, doi: 10.1080/08941920.2023.2194068.
[32] Y. Tao, W. Liu, Z. Huang, and C. Shi, “Thematic analysis of reviews on the air quality of tourist destinations from a sentiment analysis perspective,” Tour. Manag. Perspect., vol. 42, Apr. 2022, doi: 10.1016/J.TMP.2022.100969.
[33] H. K. Al-Shidi, A. K. Ambusaidi, and H. Sulaiman, “Public awareness, perceptions and attitudes on air pollution and its health effects in Muscat, Oman,” J. Air Waste Manage. Assoc., vol. 71, no. 9, pp. 1159–1174, Jan. 2021, doi: 10.1080/10962247.2021.1930287.
[34] M. von Szombathely, B. Bechtel, B. Lemke, J. Oßenbrügge, T. Pohl, and M. Pott, “Empirical evidences for urban influences on public health in Hamburg,” Applied Sciences (Switzerland), vol. 9, no. 11, p. 2303, Jun. 2019, doi: 10.3390/app9112303.
[35] Z. H. Wang et al., “Environmentally vulnerable or sensitive groups exhibiting varying concerns toward air pollution can drive government response to improve air quality,” iScience, vol. 25, no. 6, p. 104460, Jun. 2022, doi: 10.1016/j.isci.2022.104460.
[36] M. L. Loureiro, M. Alló, and P. Coello, “Hot in Twitter: Assessing the emotional impacts of wildfires with sentiment analysis,” Ecological Economics, vol. 200, p. 107502, Oct. 2022, doi: 10.1016/j.ecolecon.2022.107502.
[37] Y. Zhu et al., “Quantifying Spatiotemporal Heterogeneities in PM2.5-Related Health and Associated Determinants Using Geospatial Big Data: A Case Study in Beijing,” Remote Sens. (Basel)., vol. 14, no. 16, p. 4012, Aug. 2022, doi: 10.3390/rs14164012.
[38] “QualAr.” Accessed: Jun. 18, 2025. [Online]. Available: https://qualar.apambiente.pt/
[39] “Datos meteorológicos de SYNOPS/BUFR - Predicciones GFS/ECMWF - Meteomanz.com.” Accessed: Jun. 18, 2025. [Online]. Available: http://www.meteomanz.com/
[40] “Official Microsoft Power Automate documentation - Power Automate | Microsoft Learn.” Accessed: Jul. 02, 2025. [Online]. Available: https://learn.microsoft.com/en-us/power-automate/
[41] C. J. Hutto and E. Gilbert, “VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text,” Proceedings of the International AAAI Conference on Web and Social Media, vol. 8, no. 1, pp. 216–225, May 2014, doi: 10.1609/ICWSM.V8I1.14550.
[42] “TextBlob: Simplified Text Processing — TextBlob 0.19.0 documentation.” Accessed: Aug. 12, 2025. [Online]. Available: https://textblob.readthedocs.io/en/dev/
[43] J. J. Berman, “Understanding Your Data,” Data Simplification, pp. 135–187, 2016, doi: 10.1016/B978-0-12-803781-2.00004-7.
DOI:
https://doi.org/10.31449/inf.v50i15.13909Keywords:
Air Quality, Social Media Data, Sentiment Analysis, Environmental Dataset, Geolocated Tweets, Saharan DustDownloads
Published
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
