Volume 07 Issue 08 August 2024
Denis-Cătălin ARGHIR
Bucharest University of Economic Studies, Piața Romană, 6, Bucharest, Romania
DOI : https://doi.org/10.47191/ijsshr/v7-i08-90Google Scholar Download Pdf
ABSTRACT
This paper proposes an innovative approach for decision-makers, introducing a web application that employs a microservices architecture to analyze data gathered from social networks. In the context of smart cities, citizens act as "sensors", providing real-time insights through their online activities. By sharing locations and posting content, they generate data that can be analyzed using supervised machine learning algorithms and natural language processing techniques to identify significant urban events. The application was trained on a pre-labeled dataset from X, utilizing various machine learning models and NLP preprocessing techniques to achieve high accuracy in message classification. The dataset comprises texts with keywords related to disruptive events, such as fires, floods, heatwaves, and more severe contemporary issues like terrorism, war, or epidemics, labeled as either disruptive or neutral. Comprehensive testing was conducted using X's API, focusing on acquiring messages from specific areas. This approach can enable more proactive city management and timely resource allocation, improving overall crisis response and urban planning.
KEYWORDS:X social network, microservices web application, machine learning, natural language processing, resilient smart city, crisis management
REFERENCES1) AI/ML API. (April 01, 2024). Deciphering Grok: An In-Depth Look into Elon Musk's AI Chatbot. (AI/ML API) Retrieved June 11, 2024, from AI/ML API: a. https://aimlapi.com/blog/grok-elon-musk-ai-chatbot.
2) Arghir, D.-C. (2024). From Ancient Streets to Connected Cities: Analyzing the Implementation of Smart Initiatives in Romania. Theoretical and Empirical Researches in Urban Management, 19(2), 5-27.
3) Azhar, A., Rubab, S., Khan, M. M., Bangash, Y. A., Alshehri, M. D., Illahi, F., & Bashir, A. K. (2022). Detection and prediction of traffic accidents using deep learning techniques. Cluster Computing-The Journal of Networks Software Tools and Applications, 26(1), 477-493, Available https://doi.org/10.1007/s10586-021-03502-1.
4) Bauman, K., Tuzhilin, A., & Zaczynski, R. (2017). Using Social Sensors for Detecting Emergency Events: A Case of Power Outages in the Electrical Utility Industry. ACM Transactions on Management Information Systems, 8(2-3), 1-20, Available: a. http://dx.doi.org/10.1145/3052931.
5) Breiman, L., Friedman, J., Olshen, R., & Stone, C. J. (2017). Classification and Regression Trees. New York: Chapman and Hall/CRC.
6) Clarissa, X. C., & Marlo, S. (2018). Extraction and Classification of Semantic Data from Twitter. WEBMEDIA'18: Proceedings of the 24th Brazilian Symposium on Multimedia and the Web (pg. 15-18). Slavador: Association for Computing Machinery, Available: a. https://doi.org/10.1145/3243082.3264606.
7) ERRIN. (June 27, 2024). Advanced real-time data analysis used for infrastructure resilience. (European Regions Research and Innovation Network) Preluat pe July 17, 2024, de pe European Regions Research and Innovation Network: https://errin.eu/calls/advanced-real-time-data-analysis-used-infrastructure-resilience.
8) Gkontzis, A. F., Kotsiantis, S., Feretzakis, G., & Verykios, V. S. (2024). Enhancing Urban Resilience: Smart City Data Analyses,Forecasts, and Digital Twin Techniques at the Neighborhood Level. future internet, 16(47), 1-42, Available: https://doi.org/10.3390/fi16020047.
9) Google. Imbalanced Data. (Google) Retrieved May 20, 2024, from a. https://developers.google.com/machine-learning/data-prep/construct/sampling-splitting/imbalanced-data.
10) Kanteler, D., & Bakouros, I. (2024). A collaborative framework for cross-border disaster management in the Balkans. International Journal of Disaster Risk Reduction, 108, 1-19. Availabe: a. https://doi.org/10.1016/j.ijdrr.2024.104506.
11) Khanna, V. (February 16, 2024). Text Becomes Insight with Vectorization. (Shelf) Retrieved June 12, 2024, from Shelf: https://shelf.io/blog/text-becomes-insight-with-vectorization.
12) Maryville University. (May 28, 2020). The Evolution of Social Media: How Did It Begin, and Where Could It Go Next? (Maryville University) Retrieved June 21, 2024, from Maryville University: a. https://online.maryville.edu/blog/evolution-social-media/
13) Mehta, I. (June 27, 2023). Twitter now allows subscribers to post 25,000-character-long tweets. (Tech Crunch Yahoo News) Retrieved June 10, 2024, from Yahoo News: a. https://uk.news.yahoo.com/twitter-now-allows-subscribers-post-115307993.html.
14) Moghadas, M., Fekete, A., Rajabifard, A., & Kotter, T. (2023). The wisdom of crowds for improved disaster resilience: a near-real-time analysis of crowdsourced social media data on the 2021 flood in Germany. GeoJournal, 88, 4215-4241, Available: a. https://doi.org/10.1007/s10708-023-10858-x.
15) O'Brien, C. (December 28, 2023). How to Use Hashtags Effectively on Social Media. (Digital Marketing Institute) Retrieved June 10, 2024, from Digital Marketing Institute: a. https://digitalmarketinginstitute.com/blog/how-to-use-hashtags-in-social-media.
16) Population Media Center. (2024). 8 Billion Opportunities. (Population 8 Billion) Retrieved June 20, 2024, from https://www.populationmedia.org/population-8-billion.
17) Portal Management. (2022). 13 positive effects that social networks have on today's society. (Portal Management) Retrieved June 10, 2024, from a. https://www.portalmanagement.ro/efecte-pozitive-retelele-socializare-asupra-societatii-actuale.
18) Reveiu, A., & Arghir, D.-C. (2020). Mining Social Media to Identify the Immediate Impact of Covid-19 Pandemic on the Romanian Retailers: Early findings. 2020 Basiq International Conference: New Trends in Sustainable Business and Consumption (pg. 1225-1232). Messina: ASE.
19) Robertson, C.T. (October 25, 2023). Here’s what our research says about news audiences on Twitter, the platform now known as X. Retrieved Jul 17, 2024, from Reuters Institute: a. https://reutersinstitute.politics.ox.ac.uk/news/heres-what-our-research-says-about-news-audiences-twitter-platform-now-known-x.
20) Sagl, G., & Resch, B. (2015). Mobile Phones as Ubiquitous Social and Environmental Geo-Sensors. În Encyclopedia of Mobile Phone Behavior (pg. 1194-1213). IGI Global. Available: a. https://doi.org/10.4018/978-1-4666-8239-9.ch098.
21) scikit-learn developers. (2024) [1]. Logistic Regression. (scikit-learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html.
22) scikit learn developers. (2024) [2]. LogisticRegressionCV. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegressionCV.html.
23) scikit learn developers . (2014) [3]. Stochastic Gradient Descent. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/0.15/modules/sgd.html.
24) scikit learn developers . (2024) [4]. LinearSVC. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.svm.LinearSVC.html.
25) scikit learn developers . (2024) [5]. RandomForestClassifier. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
26) scikit learn developers. (2024) [6]. GradientBoostingClassifier. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingClassifier.html.
27) scikit learn developers . (2024) [7]. DecisionTreeClassifier. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html.
28) scikit learn developers. (2024) [8]. KNeighborsClassifier. (scikit learn developers) Retrieved May 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html.
29) scikit learn developers. (2024) [9]. BernoulliNB. (scikit learn developers) Retrieved 24, 2024, from https://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.BernoulliNB.html.
30) Sigalo, N., & Frias-Martinez, V. (2023). Using COVID-19 Vaccine Attitudes Found in Tweets to Predict Vaccine Perceptions in Traditional Surveys: Infodemiology Study. JMIR Infodemiology, 3(1), 1-15, Available: https://doi.org/10.2196/43700.
31) Siqing, S., & Feng, Z. (2023). Social media based urban disaster recovery and resilience analysis of the Henan deluge. Natural Hazards, 118, 377-405. Available: a. https://doi.org/10.1007/s11069-023-06010-0.
32) Stepanenko, V., & Liubko, I. (2020). Kaggle - Disaster Tweets Dataset. Retrieved May 10, 2024 from https://doi.org/10.34740/KAGGLE/DSV/1640141.
33) Tapia, F., Mora, M., Fuertes, W., H, A., E, F., & T, T. (2020). From Monolithic Systems to Microservices: A Comparative Study of Performance. Applied Sciences-Basel, 1-35, Available: a. https://doi.org/10.3390/app10175797.
34) Tjaden, J., & Tjaden, B. (2023). MLpronto: A tool for democratizing machine learning. PLOS ONE, 18(11), 1-12. Available: a. https://doi.org/10.1371/journal.pone.0294924.
35) Uchida, O., Kosugi, M., Endo, G., Funayama, T., Utsu, K., Tajima, S., . . . Yamamoto, Y. (2016). A Real-Time Information Sharing System to Support Self-, Mutual-, and Public-Help in the Aftermath of a Disaster Utilizing Twitter. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences, E99A(8), 1551-1554, Available: a. https://doi.org/10.1587/transfun.E99.A.1551.
36) Wang, B., Loo, B. P., Zhen, F., & Xi, G. (2020). Urban resilience from the lens of social media data: Responses to urban flooding in Nanjing, China. Cities, 106, 1-13, Available: a. https://doi.org/10.1016/j.cities.2020.102884.
37) Weiss, S. M., Indurkhya, N., Zhang, T., & Damerau, F. J. (2005). Text Mining - Predictive Methods for Analyzing Unstructured Information. Sydney: Springer.
38) X Developer Platform. (2024) [1]. Search Tweets. (X Developer Platform) Retrived June 25, 2024, from X Documentation: a. https://developer.x.com/en/docs/twitter-api/tweets/search/introduction.
39) X Developer Platform. (2024) [2]. Twitter API v2 data dictionary. (X Developer Platform) Retrived June 25, 2024, from X Documentation: a. https://developer.x.com/en/docs/twitter-api/data-dictionary/object-model/tweet.
40) Yigitcanlar, T., Regona, M., Kankanamge, N., Mehmood, R., D'Costa, J., Lindsay, S., . . . Brhane, A. (2022). Detecting Natural Hazard-Related Disaster Impacts with Social Media Analytics: The Case of Australian States and Territories. Sustainability, 14(2), 1-23, Available: a. https://doi.org/10.3390/su14020810.
41) Zisserman, A. (2015). Lecture 2: The SVM classifier. Retrived May 30, 2024, from a. https://www.robots.ox.ac.uk/~az/lectures/ml.