Sentiment Analysis of Social Network Content to Characterize the Perception of Security

Chaparro, Luisa Fernanda; Pulido, Cristian; Rudas, Jorge; Reyes, Ana María Muñoz; Victorino, Jorge; Narvaez, Luz Angela; Gómez, Francisco; Martínez, Darwin

doi:10.1109/asonam49781.2020.9381434

Cited by 10 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…8). It is worth noting that previous studies relied on small datasets [52], which are not likely exhibiting the variety of patterns related to crime on Twitter posts, which seems to be exploited by the machine learning strategy. However, despite these performance improvements, the classifier of content related to security has some limitations.…”

Section: Discussionmentioning

confidence: 99%

“…These error rates were also probably linked to the difficulty of capturing semantic feelings with single words, as suggested by lexicon-based analysis of sentiments [62], and also to the lack of contextual information [51]. Therefore, further work may explore alternative classification strategies to improve this performance [52].…”

Section: Discussionmentioning

confidence: 99%

“…A multinomial naive Bayes was used for the multiclass classification problem [51]. This classifier has been analyzed over several classifiers in previous work, and due to its performance, has been chosen as a good sentiment analysis approach [52], [53]. F1-score provided the performance measurement for validation and testing comparison.…”

Section: Sentiment Quantificationmentioning

confidence: 99%

See 2 more Smart Citations

Quantifying Perception of Security Through Social Media and Its Relationship With Crime

et al. 2021

Self Cite

View full text Add to dashboard Cite

The perception of security refers to the subjective evaluation of risks related to security events and the magnitude of their consequences. Negative perceptions have severe implications in society. These feelings are commonly quantified by citizen's surveys, which are time-consuming and do not adapt well to the changing dynamics linked to security. Recently, Twitter social network emerged as an alternative to quantify some of these feelings dynamically. However, most of these approaches focused on counting the amount of content related to crime, which is only one of the relevant factors determining the perception of security. In addition, these models do not account for the polarity and tone underlying the social network content. This work introduces a model for quantification of Perception of Security on Twitter based on sentiment analysis and studies its relationship with actual crime. The model relies on an automatic strategy for filtering content related to security based on a support vector machine classifier and quantifying the sentiment in the posts using a multinomial naive Bayes classifier. These measures of sentiment allow computing estimates of perception of security at a daily scale. This model studied more than 1.700.000 tweets in Bogotá (Colombia), collected during more than one year (March 18 of 2019 -April 28 of 2020). Results suggest that machine learning-based approaches may outperform previous security content filtering strategies by 21% in F1-score and provide quantifications on the sentiments of about 40% on accuracy. Trained models were used to provide daily estimates of perception of security, which are different from those captured by counting the number of posts related to security. Furthermore, the associations between perceptions and actual crimes exhibited monthly variations and showed that in some months, perceptions were more related to robbery, a crime with high incidence in the city. These results may help decisionmakers devise strategies to reduce the impact of the negative perception on citizens.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Sentiment Quantificationmentioning

confidence: 99%

See 1 more Smart Citation

Quantifying Perception of Security Through Social Media and Its Relationship With Crime

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some other researchers used public data to monitor and analyze citizens' feeling about security, which covers more physical aspects such as crime in a neighborhood or a city. For instance, Chaparro, Pulido, Rudas, Reyes, Victorino, Narvaez, Gomez and Martinez (2020) and Camargo, Torres, Martínez and Gómez (2016) explored Twitter data to understand behaviors of online users from specific geo-locations. Greco and Polli (2021) proposed some methods for calculating real-time public perception of cyber security measurement.…”

Section: Related Workmentioning

confidence: 99%

Perspectives of Non-Expert Users on Cyber Security and Privacy: An Analysis of Online Discussions on Twitter

Nandita¹,

Li²,

Nurse³

2022

Preprint

View full text Add to dashboard Cite

Current research on users' perspectives of cyber security and privacy related to traditional and smart devices at home is very active, but the focus is often more on specific modern devices such as mobile and smart IoT devices in a home context. In addition, most were based on smaller-scale empirical studies such as online surveys and interviews. We endeavour to fill these research gaps by conducting a larger-scale study based on a real-world dataset of 413,985 tweets posted by non-expert users on Twitter in six months of three consecutive years (January and February in 2019, 2020 and 2021). Two machine learning-based classifiers were developed to identify the 413,985 tweets. We analysed this dataset to understand non-expert users' cyber security and privacy perspectives, including the yearly trend and the impact of the COVID-19 pandemic. We applied topic modelling, sentiment analysis and qualitative analysis of selected tweets in the dataset, leading to various interesting findings. For instance, we observed a 54% increase in nonexpert users' tweets on cyber security and/or privacy related topics in 2021, compared to before the start of global COVID-19 lockdowns (January 2019 to February 2020). We also observed an increased level of help-seeking tweets during the COVID-19 pandemic. Our analysis revealed a diverse range of topics discussed by non-expert users across the three years, including VPNs, Wi-Fi, smartphones, laptops, smart home devices, financial security, and security and privacy issues involving different stakeholders. Overall negative sentiment was observed across almost all topics non-expert users discussed on Twitter in all the three years. Our results confirm the multi-faceted nature of non-expert users' perspectives on cyber security and privacy and call for more holistic, comprehensive and nuanced research on different facets of such perspectives.

show abstract

“…Os autores de [Oglesby-Neal et al 2019] focaram em uma ac ¸ão policial que resultou na morte do afro-americano Freddie Gray na cidade de Baltimores em 2015. Por sua vez, os autores de [Chaparro et al 2020] utilizaram tweets georreferenciados em Bogotá na Colômbia para identificar o sentimento da populac ¸ão sobre a seguranc ¸a nessa cidade. Cada tweet foi rotulado como um sentimento positivo ou negativo por um grupo de especialistas e os autores observaram que técnicas de aprendizagem de máquina supervisionada obtiveram acurácia e especificidade melhores que técnicas baseadas em regras léxicas.…”

Section: Trabalhos Relacionadosunclassified

Análise da Percepção das Pessoas no Twitter Sobre Ações Policiais

Feitosa¹,

Ferreira²,

Gonçalves³

et al. 2022

Anais Do XI Brazilian Workshop on Social Network Analysis and Mining (BraSNAM 2022)

View full text Add to dashboard Cite

É cada vez mais frequente o uso de redes sociais online como meio para as pessoas trocarem ideias e expressarem suas opiniões sobre diferentes aspectos do cotidiano, incluindo violência e insegurança, um problema central a vários centros urbanos. Neste artigo investigamos o potencial uso de comentários compartilhados em uma rede social bastante popular – o Twitter – para inferir a opinião pública sobre a atuação policial em incidentes de segurança de grande repercussão. Nesse sentido, exploramos atributos extraídos desses comentários e modelos de aprendizado de máquina para inferir o posicionamento das pessoas em relação a ações policiais específicas. Nossos experimentos mostram quão desafiante é essa inferência dado grande quantidade de neutralidade e sarcasmo observado em mídias sociais. Não obstante, nossos melhores classificadores alcançaram acurácia e especificidade (macro F1) superiores a 68% para inferir posicionamentos de aprovação, desaprovação e neutralidade da população.

show abstract

Sentiment Analysis of Social Network Content to Characterize the Perception of Security

Cited by 10 publications

References 15 publications

Quantifying Perception of Security Through Social Media and Its Relationship With Crime

Quantifying Perception of Security Through Social Media and Its Relationship With Crime

Perspectives of Non-Expert Users on Cyber Security and Privacy: An Analysis of Online Discussions on Twitter

Análise da Percepção das Pessoas no Twitter Sobre Ações Policiais

Contact Info

Product

Resources

About