scholarly journals Tracking Disaster Footprints with Social Streaming Data

2020 ◽  
Vol 34 (01) ◽  
pp. 370-377
Author(s):  
Lu Cheng ◽  
Jundong Li ◽  
K. Selcuk Candan ◽  
Huan Liu
Keyword(s):  
Social Media ◽  
Nonnegative Matrix ◽  
Reconstruction Error ◽  
Streaming Data ◽  
Accurate Information ◽  
Topic Identification ◽  
Emergency Managers ◽  
Naive Method ◽  
Real World Datasets ◽  
Over Time

Social media has become an indispensable tool in the face of natural disasters due to its broad appeal and ability to quickly disseminate information. For instance, Twitter is an important source for disaster responders to search for (1) topics that have been identified as being of particular interest over time, i.e., common topics such as “disaster rescue”; (2) new emerging themes of disaster-related discussions that are fast gathering in social media streams (Saha and Sindhwani 2012), i.e., distinct topics such as “the latest tsunami destruction”. To understand the status quo and allocate limited resources to most urgent areas, emergency managers need to quickly sift through relevant topics generated over time and investigate their commonness and distinctiveness. A major obstacle to the effective usage of social media, however, is its massive amount of noisy and undesired data. Hence, a naive method, such as set intersection/difference to find common/distinct topics, is often not practical. To address this challenge, this paper studies a new topic tracking problem that seeks to effectively identify the common and distinct topics with social streaming data. The problem is important as it presents a promising new way to efficiently search for accurate information during emergency response. This is achieved by an online Nonnegative Matrix Factorization (NMF) scheme that conducts a faster update of latent factors, and a joint NMF technique that seeks the balance between the reconstruction error of topic identification and the losses induced by discovering common and distinct topics. Extensive experimental results on real-world datasets collected during Hurricane Harvey and Florence reveal the effectiveness of our framework.

scholarly journals Retaining Data from Streams of Social Platforms with Minimal Regret

2017 ◽  
Author(s):  
Nguyen Thanh Tam ◽  
Matthias Weidlich ◽  
Duong Chi Thang ◽  
Hongzhi Yin ◽  
Nguyen Quoc Viet Hung
Keyword(s):  
Social Media ◽  
Data Streams ◽  
Large Scale ◽  
Information Quality ◽  
Streaming Data ◽  
Dynamic Nature ◽  
Permanent Storage ◽  
Reasonable Limit ◽  
Efficient Processing ◽  
Real World Datasets

Today's social platforms, such as Twitter and Facebook, continuously generate massive volumes of data. The resulting data streams exceed any reasonable limit for permanent storage, especially since data is often redundant, overlapping, sparse, and generally of low value. This calls for means to retain solely a small fraction of the data in an online manner. In this paper, we propose techniques to effectively decide which data to retain, such that the induced loss of information, the regret of neglecting certain data, is minimized. These techniques enable not only efficient processing of massive streaming data, but are also adaptive and address the dynamic nature of social media. Experiments on large-scale real-world datasets illustrate the feasibility of our approach in terms of both, runtime and information quality.

The use of social media for campus safety

2017 ◽  
Vol 15 (1) ◽  
pp. 17 ◽  
Author(s):  
Brittany Haupt, MEd ◽  
Naim Kapucu, PhD ◽  
Jeffrey Morgan, MA
Keyword(s):  
Social Media ◽  
Public Safety ◽  
Cost Effective ◽  
Future Research ◽  
Accurate Information ◽  
Campus Community ◽  
Safety Communication ◽  
Emergency Managers ◽  
Campus Emergency Management ◽  
Use Of Social Media

As public safety communication evolved, each disaster or emergency presented unique challenges for emergency managers and others response to disasters. Yet, a foundational focus is the timely dissemination of accurate information to keep communities informed and able to prepare, mitigate, respond, and recover. For the campus community, the increase in bomb threats, active shooter incidents, and geographic-based natural disasters call for the discovery of reliable and cost-effective solutions for emergency information management. Social media is becoming a critical asset in this endeavor. This article examines the evolution of public safety communication, the unique setting of the campus community, and social media's role in campus disaster resilience. In addition, an exploratory study was done to better understand the perception of social media use for public safety within the campus community. The findings provide practical recommendations for campus emergency management professions; however, future research is needed to provide specific, actionable ways to achieve these goals as well as understand how diverse universities utilize a variety of platforms.

scholarly journals Evaluating Cultural Impact in Discursive Space through Digital Footprints

2021 ◽  
Vol 13 (7) ◽  
pp. 4043 ◽  
Author(s):  
Jesús López Baeza ◽  
Jens Bley ◽  
Kay Hartkopf ◽  
Martin Niggemann ◽  
James Arias ◽  
...  
Keyword(s):  
Social Media ◽  
Language Processing ◽  
Social Activity ◽  
Test Site ◽  
Cultural Discourse ◽  
Discursive Space ◽  
Topic Identification ◽  
Small Test ◽  
The Impact ◽  
The City

The research presented in this paper describes an evaluation of the impact of spatial interventions in public spaces, measured by social media data. This contribution aims at observing the way a spatial intervention in an urban location can affect what people talk about on social media. The test site for our research is Domplatz in the center of Hamburg, Germany. In recent years, several actions have taken place there, intending to attract social activity and spotlight the square as a landmark of cultural discourse in the city of Hamburg. To evaluate the impact of this strategy, textual data from the social networks Twitter and Instagram (i.e., tweets and image captions) are collected and analyzed using Natural Language Processing intelligence. These analyses identify and track the cultural topic or “people talking about culture” in the city of Hamburg. We observe the evolution of the cultural topic, and its potential correspondence in levels of activity, with certain intervention actions carried out in Domplatz. Two analytic methods of topic clustering and tracking are tested. The results show a successful topic identification and tracking with both methods, the second one being more accurate. This means that it is possible to isolate and observe the evolution of the city’s cultural discourse using NLP. However, it is shown that the effects of spatial interventions in our small test square have a limited local scale, rather than a city-wide relevance.

Knowledge-aware Multi-modal Adaptive Graph Convolutional Networks for Fake News Detection

2021 ◽  
Vol 17 (3) ◽  
pp. 1-23
Author(s):  
Shengsheng Qian ◽  
Jun Hu ◽  
Quan Fang ◽  
Changsheng Xu
Keyword(s):  
Social Media ◽  
Visual Information ◽  
Representation Learning ◽  
Fake News ◽  
Unified Framework ◽  
Model Learning ◽  
Convolutional Network ◽  
Textual Information ◽  
Convolutional Networks ◽  
Real World Datasets

In this article, we focus on fake news detection task and aim to automatically identify the fake news from vast amount of social media posts. To date, many approaches have been proposed to detect fake news, which includes traditional learning methods and deep learning-based models. However, there are three existing challenges: (i) How to represent social media posts effectively, since the post content is various and highly complicated; (ii) how to propose a data-driven method to increase the flexibility of the model to deal with the samples in different contexts and news backgrounds; and (iii) how to fully utilize the additional auxiliary information (the background knowledge and multi-modal information) of posts for better representation learning. To tackle the above challenges, we propose a novel Knowledge-aware Multi-modal Adaptive Graph Convolutional Networks (KMAGCN) to capture the semantic representations by jointly modeling the textual information, knowledge concepts, and visual information into a unified framework for fake news detection. We model posts as graphs and use a knowledge-aware multi-modal adaptive graph learning principal for the effective feature learning. Compared with existing methods, the proposed KMAGCN addresses challenges from three aspects: (1) It models posts as graphs to capture the non-consecutive and long-range semantic relations; (2) it proposes a novel adaptive graph convolutional network to handle the variability of graph data; and (3) it leverages textual information, knowledge concepts and visual information jointly for model learning. We have conducted extensive experiments on three public real-world datasets and superior results demonstrate the effectiveness of KMAGCN compared with other state-of-the-art algorithms.

scholarly journals Framing of visual content shown on popular social media may affect viewers’ attitudes to threatened species

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Fernando Ballejo ◽  
Pablo Ignacio Plaza ◽  
Sergio Agustín Lambertucci
Keyword(s):  
Social Media ◽  
Threatened Species ◽  
Social Medium ◽  
Visual Content ◽  
Wildlife Species ◽  
Mammalian Predators ◽  
Negative Comments ◽  
Over Time ◽  
The Way

AbstractContent published on social media may affect user’s attitudes toward wildlife species. We evaluated viewers’ responses to videos published on a popular social medium, focusing particularly on how the content was framed (i.e., the way an issue is conveyed to transmit a certain meaning). We analyzed videos posted on YouTube that showed vultures interacting with livestock. The videos were negatively or positively framed, and we evaluated viewers’ opinions of these birds through the comments posted. We also analyzed negatively framed videos of mammalian predators interacting with livestock, to evaluate whether comments on this content were similar to those on vultures. We found that the framing of the information influenced the tone of the comments. Videos showing farmers talking about their livestock losses were more likely to provoke negative comments than videos not including farmer testimonies. The probability of negative comments being posted on videos about vultures was higher than for mammalian predators. Finally, negatively framed videos on vultures had more views over time than positive ones. Our results call for caution in the presentation of wildlife species online, and highlight the need for regulations to prevent the spread of misinformed videos that could magnify existing human-wildlife conflicts.

Factor-Bounded Nonnegative Matrix Factorization

2021 ◽  
Vol 15 (6) ◽  
pp. 1-18
Author(s):  
Kai Liu ◽  
Xiangyu Li ◽  
Zhihui Zhu ◽  
Lodewijk Brand ◽  
Hua Wang
Keyword(s):  
Matrix Factorization ◽  
Clustering Algorithm ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Optimization Methods ◽  
Auxiliary Function ◽  
Image Clustering ◽  
Real World Datasets ◽  
The Relationship ◽  
Matrix Factors

Nonnegative Matrix Factorization (NMF) is broadly used to determine class membership in a variety of clustering applications. From movie recommendations and image clustering to visual feature extractions, NMF has applications to solve a large number of knowledge discovery and data mining problems. Traditional optimization methods, such as the Multiplicative Updating Algorithm (MUA), solves the NMF problem by utilizing an auxiliary function to ensure that the objective monotonically decreases. Although the objective in MUA converges, there exists no proof to show that the learned matrix factors converge as well. Without this rigorous analysis, the clustering performance and stability of the NMF algorithms cannot be guaranteed. To address this knowledge gap, in this article, we study the factor-bounded NMF problem and provide a solution algorithm with proven convergence by rigorous mathematical analysis, which ensures that both the objective and matrix factors converge. In addition, we show the relationship between MUA and our solution followed by an analysis of the convergence of MUA. Experiments on both toy data and real-world datasets validate the correctness of our proposed method and its utility as an effective clustering algorithm.

Do Materialistic Adolescents Ruminate More About Their Social Media Posts?

2020 ◽  
pp. 0044118X2098417
Author(s):  
Keeley Hynes ◽  
Daniel G. Lannin ◽  
Jeremy B. Kanter ◽  
Ani Yazedjian ◽  
Margaret M. Nauta
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Social Status ◽  
Mental Distress ◽  
External Validation ◽  
Value Orientation ◽  
Media Content ◽  
Over Time

Previous research suggests that ruminating on social media content is associated with greater mental distress (Yang et al., 2018). This study examined whether materialistic value orientation (MVO)—prioritizing values and goals related to consumerism, consumption, and social status—predicted social media rumination in a sample of diverse adolescents in a two-wave cross-lagged design. A cross-lagged analysis among 119 adolescents indicated that MVO at Wave 1 predicted greater social media rumination 4 months later at Wave 2, but social media rumination at Wave 1 did not predict MVO at Wave 2. Cross-lagged results suggested that MVO may lead to greater social media rumination over time for diverse adolescents. Adolescents with MVO could benefit from interventions to reduce the effects of their need for external validation and maladaptive rumination, as external validation and maladaptive rumination are linked to behaviors and thoughts that can be harmful to mental health.

Dynamics of convergence behaviour in social media crisis communication – a complexity perspective

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Milad Mirbabaie ◽  
Stefan Stieglitz ◽  
Felix Brünker
Keyword(s):  
Social Media ◽  
Emergency Management ◽  
Crisis Communication ◽  
Design Methodology ◽  
Content Type ◽  
The Public ◽  
Analysis Techniques ◽  
Twitter Data ◽  
Convergence Behaviour ◽  
Over Time

PurposeThe purpose of this study is to investigate communication on Twitter during two unpredicted crises (the Manchester bombings and the Munich shooting) and one natural disaster (Hurricane Harvey). The study contributes to understanding the dynamics of convergence behaviour archetypes during crises.Design/methodology/approachThe authors collected Twitter data and analysed approximately 7.5 million relevant cases. The communication was examined using social network analysis techniques and manual content analysis to identify convergence behaviour archetypes (CBAs). The dynamics and development of CBAs over time in crisis communication were also investigated.FindingsThe results revealed the dynamics of influential CBAs emerging in specific stages of a crisis situation. The authors derived a conceptual visualisation of convergence behaviour in social media crisis communication and introduced the terms hidden and visible network-layer to further understanding of the complexity of crisis communication.Research limitations/implicationsThe results emphasise the importance of well-prepared emergency management agencies and support the following recommendations: (1) continuous and (2) transparent communication during the crisis event as well as (3) informing the public about central information distributors from the start of the crisis are vital.Originality/valueThe study uncovered the dynamics of crisis-affected behaviour on social media during three cases. It provides a novel perspective that broadens our understanding of complex crisis communication on social media and contributes to existing knowledge of the complexity of crisis communication as well as convergence behaviour.

Gamifying the Media Classroom

2017 ◽  
Vol 7 (4) ◽  
pp. 22-49
Author(s):  
Katie Seaborn ◽  
Deborah I. Fels ◽  
Rob Bajko ◽  
Jaigris Hodson
Keyword(s):  
Social Media ◽  
Student Engagement ◽  
Conceptual Framework ◽  
Student Perspective ◽  
Educational Settings ◽  
The Media ◽  
Game Elements ◽  
The Impact ◽  
Over Time

Gamification, or the use of game elements in non-game contexts, has become a popular and increasingly accepted method of engaging learners in educational settings. However, there have been few comparisons of different kinds of courses and students, particularly in terms of discipline and content. Additionally, little work has reported on course instructor/designer perspectives. Finally, few studies on gamification have used a conceptual framework to assess the impact on student engagement. This paper reports on findings from evaluating two gamified multimedia and social media undergraduate courses over the course of one semester. Findings from applying a multidimensional framework suggest that the gamification approach taken was moderately effective for students overall, with some elements being more engaging than others in general and for each course over time." Post-term questionnaires posed to the instructors/course designers revealed congruence with the student perspective and several challenges pre- and post-implementation, despite the use of established rules for gamifying curricula.

scholarly journals Polarization in the contemporary political and media landscape

2020 ◽  
Author(s):  
Anne E Wilson ◽  
Victoria Parker ◽  
Matthew Feinberg
Keyword(s):  
Social Media ◽  
Political Polarization ◽  
Political Elites ◽  
Ideological Polarization ◽  
Societal Level ◽  
Polarization Phenomena ◽  
Partisan Media ◽  
Over Time

Political polarization is on the rise in America. Although social psychologists frequently study the intergroup underpinnings of polarization, they have traditionally had less to say about macro societal processes that contribute to its rise and fall. Recent cross-disciplinary work on the contemporary political and media landscape provides these complementary insights. In this paper, we consider the evidence for and implications of political polarization, distinguishing between ideological, affective, and false polarization. We review three key societal-level factors contributing to these polarization phenomena: the role of political elites, partisan media, and social media dynamics. We argue that institutional polarization processes (elites, media and social media) contribute to people’s misperceptions of division among the electorate, which in turn can contribute to a self-perpetuating cycle fueling animosity (affective polarization) and actual ideological polarization over time.

Sign in / Sign up

Export Citation Format

Share Document