Event Detection System Based on User Behavior Changes in Online Social Networks: Case of the COVID-19 Pandemic

Abstract

People use Online Social Networks (OSNs) to express their opinions and feelings about many topics. Depending on the nature of an event and its dissemination rate in OSNs, and considering specific regions, the users' behavior can drastically change over a specific period of time. In this context, this work aims to propose an event detection system at the early stages of an event based on changes in the users' behavior in an OSN. This system can detect an event of any subject, and thus, it can be used for different purposes. The proposed event detection system is composed of the following main modules: (1) determination of the user's location, (2) message extraction from an OSN, (3) topic identification using natural language processing (NLP) based on the Deep Belief Network (DBN), (4) the user behavior change analyzer in the OSN, and (5) affective analysis for emotion identification based on a tree-convolutional neural network (tree-CNN). In the case of public health, the early event detection is very relevant for the population and the authorities in order to be able take corrective actions. Hence, the new coronavirus disease (COVID-19) is used as a case study in this work. For performance validation, the modules related to the topic identification and affective analysis were compared with other similar solutions or implemented with other machine learning algorithms. In the performance assessment, the proposed event detection system achieved an accuracy higher than 0.90, while other similar methods reached accuracy values less than 0.74. Additionally, our proposed system was able to detect an event almost three days earlier than the other methods. Furthermore, the information provided by the system permits to understand the predominant characteristics of an event, such as keywords and emotion type of messages. INDEX TERMS Event detection, Online Social Networks, affective analysis, natural language processing, COVID-19.

Containing Future Epidemics With Trustworthy Federated Systems for Ubiquitous Warning and Response

“…For instance, in Li et al (2020), authors collected comments posted in the Chinese social media channel Weibo during the first month of the COVID-19 epidemic in Wuhan (China) to understand the evolution trend of the public opinion. A similar approach was used on Twitter in Alshaabi et al (2020) and Rosa et al (2020). Government entities can use this approach to give more attention to the needs of the public during the beginning of the epidemic and adjust their responses accordingly.…”

Can Social Media Data Be Utilized to Enhance Early Warning: Retrospective Analysis of the U.S. Covid-19 Pandemic

“…Their experiment results displayed a high correlation with influenza cases that outperforms the Google search method. Rosa et al adopted topic modeling techniques to analyze users' behavior changes in online social networks [43]. They have applied their model to detect the COVID-19 pandemic in the early stages.…”

“…Rosa et al . adopted topic modeling techniques to analyze users’ behavior changes in online social networks [43]. They have applied their model to detect the COVID-19 pandemic in the early stages.…”

Event detection in finance using hierarchical clustering algorithms on news and tweets

“…In this sense, Event Detection aims to discover contents published on the Web that report on the same current topic, organize them in meaningful groups and provide insights, based on properties extracted automatically from the data ( Allan, Papka & Lavrenko, 1998 , Hu et al, 2017 ). It represents a valuable resource to create awareness and support decision making in various domains of application, including epidemics ( Aramaki, Maskawa & Morita, 2011 ; Rosa et al, 2020 ), earthquakes ( Sakaki, Okazaki & Matsuo, 2010 ), social events ( Petkos, Papadopoulos & Kompatsiaris, 2012 ) and economy (see “Event Detection in Finance”), among others. In some cases, the scope of the event detection task is not limited to arranging the contents and providing analytics, but constitutes the basis for further algorithmic processing, like for example the development of automatic trading strategies in financial applications ( Gilbert & Karahalios, 2010 ; Ruiz et al, 2012 ; Makrehchi, Shah & Liao, 2013 ).…”