More Like this

1. Data Analysis and Visualization of Crime Data

   https://doi.org/10.2352/EI.2024.36.1.VDA-364  

   Sharma, Sharad; Dronavalli, Sri Chandra (January 2024, Electronic Imaging)

   The rise in crime rates over the past few years is a major issue and is a huge source of worry for police departments and law enforcement organizations. Crime severely harms the lives of victims and the communities they live in many places throughout the world. It is an issue of public disturbance, and large cities often see criminal activity. Many studies, media, and websites include statistics on crime and it is contributing elements, such as population, unemployment, and poverty rate. This paper compares and visualizes the crime data for four different cities in the USA, namely Chicago, Baltimore, Dallas, and Denton. We assess areas that are significantly affected based on zip codes and variations in crime categories. As the crime rates have significantly changed both upward and downward throughout time, these changes are compared to their external causes such as population, unemployment, and poverty. The results show crime frequency and distribution across four different cities and supply valuable information about the complex relationship between social factors and criminal behavior. These results and outcomes will help the police department and law enforcement organizations better understand crime issues, map crime incidents onto a geographical map, and supply insight into factors affecting crime that will help them deploy resources and help in their decision-making process. 

   more » « less
2. A Multi-Input Multi-Output Transformer-Based Hybrid Neural Network for Multi-Class Privacy Disclosure Detection

   https://doi.org/10.5121/csit.2021.111419  

   Mehdy, A K; Mehrpouyan, Hoda (September 2021, 2nd International Conference on Advances in Software Engineering (ASOFT 2021))

   The concern regarding users’ data privacy has risen to its highest level due to the massive increase in communication platforms, social networking sites, and greater users’ participation in online public discourse. An increasing number of people exchange private information via emails, text messages, and social media without being aware of the risks and implications. Researchers in the field of Natural Language Processing (NLP) have concentrated on creating tools and strategies to identify, categorize, and sanitize private information in text data since a substantial amount of data is exchanged in textual form. However, most of the detection methods solely rely on the existence of pre-identified keywords in the text and disregard the inference of underlying meaning of the utterance in a specific context. Hence, in some situations these tools and algorithms fail to detect disclosure, or the produced results are miss classified. In this paper, we propose a multi-input, multi-output hybrid neural network which utilizes transfer-learning, linguistics, and metadata to learn the hidden patterns. Our goal is to better classify disclosure/non-disclosure content in terms of the context of situation. We trained and evaluated our model on a human-annotated ground truth dataset, containing a total of 5,400 tweets. The results show that the proposed model was able to identify privacy disclosure through tweets with an accuracy of 77.4% while classifying the information type of those tweets with an impressive accuracy of 99%, by jointly learning for two separate tasks. 

   more » « less
3. Evaluating LLMs Capabilities Towards Understanding Social Dynamics

   Tahir, A; Cheng, L; Sandoval, M; Silva, Y N; Hall, D; Liu, H (September 2024, The 2024 International Conference on Advances in Social Networks Analysis and Mining (ASONAM))

   Social media discourse involves people from different backgrounds, beliefs, and motives. Thus, often such discourse can devolve into toxic interactions. Generative Models, such as Llama and ChatGPT, have recently exploded in popularity due to their capabilities in zero-shot question-answering. Because these models are increasingly being used to ask questions of social significance, a crucial research question is whether they can understand social media dynamics. This work provides a critical analysis regarding generative LLM’s ability to understand language and dynamics in social contexts, particularly considering cyberbullying and anti-cyberbullying (posts aimed at reducing cyberbullying) interactions. Specifically, we compare and contrast the capabilities of different large language models (LLMs) to understand three key aspects of social dynamics: language, directionality, and the occurrence of bullying/anti-bullying messages. We found that while fine-tuned LLMs exhibit promising results in some social media understanding tasks (understanding directionality), they presented mixed results in others (proper paraphrasing and bullying/anti-bullying detection). We also found that fine-tuning and prompt engineering mechanisms can have positive effects in some tasks. We believe that a understanding of LLM’s capabilities is crucial to design future models that can be effectively used in social applications. 

   more » « less
4. From Posts to Pavement, or Vice Versa? The Dynamic Interplay between Online Activism and Offline Confrontations

   https://doi.org/10.1609/icwsm.v18i1.31418  

   Yan, Muheng; Chiang, Amy Yunyu; Lin, Yu-Ru (May 2024, Proceedings of the International AAAI Conference on Web and Social Media)

   This study examines how the relationship between social media discourse and offline confrontations in social movements, focusing on the Black Lives Matter (BLM) protests following George Floyd's death in 2020. While social media's role in facilitating social movements is well-documented, its relationship with offline confrontations remains understudied. To bridge this gap, we curated a dataset comprising 108,443 Facebook posts and 1,406 offline BLM protest events. Our analysis categorized online media framing into consonance (alignment) and dissonance (misalignment) with the perspectives of different involved parties. Our findings indicate a reciprocal relationship between online activism support and offline confrontational occurrences. Online support for the BLM, in particular, was associated with less property damage and fewer confrontational protests in the days that followed. Conversely, offline confrontations amplified online support for the protesters. By illuminating this dynamic, we highlight the multifaceted influence of social media on social movements. Not only does it serve as a platform for information dissemination and mobilization but also plays a pivotal role in shaping public discourse about offline confrontations. 

   more » « less
5. Getting Local and Personal: Toward Building a Predictive Model for COVID in Three United States Cities.

   Edwards, April; Metcalf, Leigh; Casey, William A; Chatterjee, Shirshendu; Janwa, Heeralal; Battifarano, Ernest (May 2023, Springer)

   Kacprzyk, Janusz; Pal, Nikhil R; Perez, Rafael B; Corchado, Emilio S; Hagras, Hani; Kóczy, László T; Kreinovich, Vladik; Lin, Chin-Teng; Lu, Jie; Melin, Patricia (Ed.)

   The COVID-19 pandemic was lived in real-time on social media. In the current project, we use machine learning to explore the relationship between COVID-19 cases and social media activity on Twitter. We were particularly interested in determining if Twitter activity can be used to predict COVID-19 surges. We also were interested in exploring features of social media, such as replies, to determine their promise for understanding the views of individual users. With the prevalence of mis/disinformation on social media, it is critical to develop a deeper and richer understanding of the relationship between social media and real-world events in order to detect and prevent future influence operations. In the current work, we explore the relationship between COVID-19 cases and social media activity (on Twitter) in three major United States cities with different geographical and political landscapes. We find that Twitter activity resulted in statistically significant correlations using the Granger causality test, with a lag of one week in all three cities. Similarly, the use of replies, which appear more likely to be generated by individual users, not bots or public relations operations, was also strongly correlated with the number of COVID-19 cases using the Granger causality test. Furthermore, we were able to build promising predictive models for the number of future COVID-19 cases using correlation data to select features for input to our models. In contrast, significant correlations were not identified when comparing the number of COVID-19 cases with mainstream media sources or with a sample of all US COVID-related tweets. We conclude that, even for an international event such as COVID-19, social media tracks closely with local conditions. We also suggest that replies can be a valuable feature within a machine learning task that is attempting to gauge the reactions of individual users. 

   more » « less