Detecting prominent microblog users over crisis events phases

Abstract

During crisis events such as disasters, the need for real-time information retrieval (IR) from microblogs becomes essential. However, the huge amount and the variety of the shared information in real time during such events over-complicates this task. Unlike existing IR approaches based on content analysis, we propose to tackle this problem by using user-centric IR approaches with identifying and tracking prominent microblog users who are susceptible to share relevant and exclusive information at an early stage of each analyzed event phase. This approach ensures real-time access to the valuable microblogs information required by the emergency teams. In this approach, we propose a phase-aware probabilistic model for predicting and ranking prominent microblog users over time according to their behavior using Mixture of Gaussians Hidden Markov Models (MoG-HMM). The model utilizes a new user representation which takes into account both the user and the event specificities over time. This user representation comprises the following new aspects (1) Modeling microblog users behavior evolution by considering the different event phases (2) Characterizing users activity over time through a temporal sequence representation (3) Timeseries-based selection of the most discriminative features (4) prominent users prediction using probabilistic phase-aware models learned a priori. We have conducted experiments during flooding events: we trained our identification models using a dataset relative to the "Alpes-Maritimes floods" and we tested its identification performance using a new dataset relative to another flooding disaster "Herault floods". The achieved results show that our model significantly outperforms phase-unaware models and identifies most of the prominent users at an early stage of each event phase.

Concerns Expressed by Chinese Social Media Users During the COVID-19 Pandemic: Content Analysis of Sina Weibo Microblogging Data

“…Sina Weibo, with over 500 million users by May 2020, provides a variety of communication mechanisms for citizen interaction, allowing the Chinese public to share information and exchange opinions [ 9 - 11 ]. By analyzing the concerns raised by citizens about COVID-19 in microblog posts shared on Sina Weibo, governments can better understand public attitudes and demands [ 12 , 13 ] and clarify existing challenges faced by government departments and organizations when dealing with the pandemic. This research provides important insights and implications for policy makers, especially those working in public health departments.…”

A customisable pipeline for the semi-automated discovery of online activists and social campaigns on Twitter

“…Topical Strength [5] : T S(u) = P 2 on (u) • log(P 2 on (u)+R3 on +1) P 2 off (u) • log(P 2 off (u)+R3 off +1)+1…”

“…Greater sized contexts with more harvested tweets may increase the number of harvested users as well as better define them in terms of metrics. As an example, in [5], where the goal is to identify prominent information-sharing users during natural disasters, two datasets are used. The first one contains 152 402 tweets shared by 21 364, while the other consists of 44 330 tweets shared by 3 338 users.…”

“…The Twitter APIs, because of the severe usage quota limitations, may represent a problem in the case of greater implementations of the framework. This limit can be overcome by using multiple Twitter developer accounts as done in [5], where 5 hosts and 30 developers accounts where used. Table 1 lists the events along with key metrics for their corresponding user-user networks.…”

Study on the application of government affairs micro-blog in the disclosure of government emergency information in China

“…Researchers are also seeking new ways of applying micro-blogs to crisis management. For example, Bizid et al (2018) proposed a new approach named Phase-aware Micro-blog Users Modeling to help predict prominent micro-blog users at an early stage of each event and user-centric IR approaches to identify and track the prominent micro-blog users who are susceptible to sharing relevant and exclusive information at the early stages of an event, which ensures real-time access to valuable micro-blogs information required by an emergency team. Sarah et al (2010) analyzed micro-blog posts generated via Twitter during two concurrent emergency events in North America in order to use information extraction techniques to predict the next steps during emergencies.…”