scholarly journals Prototyping a Social Media Flooding Photo Screening System Based on Deep Learning

2020 ◽  
Vol 9 (2) ◽  
pp. 104 ◽  
Author(s):  
Huan Ning ◽  
Zhenlong Li ◽  
Michael E. Hodgson ◽  
Cuizhen (Susan) Wang
Keyword(s):  
Social Media ◽  
Visual Information ◽  
Decision Makers ◽  
Training Dataset ◽  
Screening System ◽  
Flood Events ◽  
Training Set ◽  
Photo Detection ◽  
Damage Impact ◽  
Total Accuracy

This article aims to implement a prototype screening system to identify flooding-related photos from social media. These photos, associated with their geographic locations, can provide free, timely, and reliable visual information about flood events to the decision-makers. This screening system, designed for application to social media images, includes several key modules: tweet/image downloading, flooding photo detection, and a WebGIS application for human verification. In this study, a training dataset of 4800 flooding photos was built based on an iterative method using a convolutional neural network (CNN) developed and trained to detect flooding photos. The system was designed in a way that the CNN can be re-trained by a larger training dataset when more analyst-verified flooding photos are being added to the training set in an iterative manner. The total accuracy of flooding photo detection was 93% in a balanced test set, and the precision ranges from 46–63% in the highly imbalanced real-time tweets. The system is plug-in enabled, permitting flexible changes to the classification module. Therefore, the system architecture and key components may be utilized in other types of disaster events, such as wildfires, earthquakes for the damage/impact assessment.

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 Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

scholarly journals Change in Evaluation Mode Can Cause a Cheerleader Effect

2021 ◽  
Vol 12 ◽  
Author(s):  
Claude Messner ◽  
Mattia Carnelli ◽  
Patrick Stefan Hähener
Keyword(s):  
Social Media ◽  
Visual Information ◽  
Visual Memory ◽  
Target Face ◽  
Contrast Effects ◽  
Evaluation Mode ◽  
Standard Of Comparison ◽  
Low Levels ◽  
Hierarchical Encoding ◽  
Practical Implications

The cheerleader effect describes the phenomenon whereby faces are perceived as being more attractive when flanked by other faces than when they are perceived in isolation. At least four theories predict the cheerleader effect. Two visual memory processes could cause a cheerleader effect. First, visual information will sometimes be averaged in the visual memory: the averaging of faces could increase the perceived attractiveness of all the faces flanked by other faces. Second, information will often be combined into a higher-order concept. This hierarchical encoding suggests that information processing causes faces to appear more attractive when flanked by highly attractive faces. Two further explanations posit that comparison processes cause the cheerleader effect. While contrast effects predict that a difference between the target face and the flanking faces causes the cheerleader effect due to comparison processes, a change in the evaluation mode, which alters the standard of comparison between joint and separate evaluation of faces, could be sufficient for producing a cheerleader effect. This leads to the prediction that even when there is no contrast between the attractiveness of the target face and the flanking faces, a cheerleader effect could occur. The results of one experiment support this prediction. The findings of this study have practical implications, such as for individuals who post selfies on social media. An individual’s face will appear more attractive in a selfie taken with people of low attractiveness than in a selfie without other people, even when all the faces have equally low levels of attractiveness.

scholarly journals The Content Analysis of Social Media Shares in Turkish Related to COVID-19

2021 ◽  
Vol 11 (3) ◽  
pp. 113-137
Author(s):  
M. Fevzi Esen
Keyword(s):  
Social Media ◽  
Content Analysis ◽  
Information Source ◽  
Latent Semantic Indexing ◽  
Decision Makers ◽  
Semantic Indexing ◽  
Social Media Networks ◽  
Network Analyses ◽  
Media Platform ◽  
Short Time

A remarkable increase has currently been happening in social media platform content related to COVID-19. Users have created large volumes of content on various topics over a short time, interacting with people in real-time. This also has transformed social media into an indispensable information source for any crisis. This study aims to explore the information content on COVID-19 disseminated through social media and to discover prominent topics in shares on COVID-19. In this regard, we have retrieved 17,542 tweets shared in Turkish. A content analysis of social media shares has been carried out, with latent semantic indexing and network analyses being performed to detect the relationships and interactions among shares. As a result, the most shared topics have been concluded to be on yasak [lockdown], tedbir [precaution], karantina [quarantine], and vaka [case], with communication being frequently passed using this semantic string and information exchanges being faster within the network. In addition, shares related to hygiene, masks, and distancing were determined to have occurred less than shares related to precautions, rules, cases, and lockdowns. The number of likes and retweets for content with social propaganda such as #evdekal [stayathome], #evdehayatvar [lifeathome], and #birliktebaşaracağız [togetherwesucceed] were low and not found in a semantic string. This suggests social propaganda through social media to have had a limited impact on epidemic management. In conclusion, identifying the prominent issues in social media posts and the characteristics of social media networks will help decision-makers determine appropriate policies for controlling and preventing the pandemic’s spread.

Detection of misinformation on garlic and COVID-19 in Twitter: A machine learning-based approach (Preprint)

2021 ◽  
Author(s):  
Myeong Gyu Kim ◽  
Jae Hyun Kim ◽  
Kyungim Kim
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Latent Dirichlet Allocation ◽  
Predictive Performance ◽  
Machine Learning Algorithms ◽  
Training Dataset ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Accurate Information ◽  
Probability Number

BACKGROUND Garlic-related misinformation is prevalent whenever a virus outbreak occurs. Again, with the outbreak of coronavirus disease 2019 (COVID-19), garlic-related misinformation is spreading through social media sites, including Twitter. Machine learning-based approaches can be used to detect misinformation from vast tweets. OBJECTIVE This study aimed to develop machine learning algorithms for detecting misinformation on garlic and COVID-19 in Twitter. METHODS This study used 5,929 original tweets mentioning garlic and COVID-19. Tweets were manually labeled as misinformation, accurate information, and others. We tested the following algorithms: k-nearest neighbors; random forest; support vector machine (SVM) with linear, radial, and polynomial kernels; and neural network. Features for machine learning included user-based features (verified account, user type, number of followers, and follower rate) and text-based features (uniform resource locator, negation, sentiment score, Latent Dirichlet Allocation topic probability, number of retweets, and number of favorites). A model with the highest accuracy in the training dataset (70% of overall dataset) was tested using a test dataset (30% of overall dataset). Predictive performance was measured using overall accuracy, sensitivity, specificity, and balanced accuracy. RESULTS SVM with the polynomial kernel model showed the highest accuracy of 0.670. The model also showed a balanced accuracy of 0.757, sensitivity of 0.819, and specificity of 0.696 for misinformation. Important features in the misinformation and accurate information classes included topic 4 (common myths), topic 13 (garlic-specific myths), number of followers, topic 11 (misinformation on social media), and follower rate. Topic 3 (cooking recipes) was the most important feature in the others class. CONCLUSIONS Our SVM model showed good performance in detecting misinformation. The results of our study will help detect misinformation related to garlic and COVID-19. It could also be applied to prevent misinformation related to dietary supplements in the event of a future outbreak of a disease other than COVID-19.

Assessment of Flood Early Warning Systems with Social Media

2021 ◽  
Author(s):  
Thierry Hohmann ◽  
Judit Lienert ◽  
Jafet Andersson ◽  
Darcy Molnar ◽  
Peter Molnar ◽  
...  
Keyword(s):  
Social Media ◽  
Performance Assessment ◽  
Early Warning ◽  
Early Warning Systems ◽  
Probability Of Detection ◽  
Economic Losses ◽  
Warning Systems ◽  
Flood Events ◽  
Spatial Coverage ◽  
De Bruijn

<p><strong>Introduction</strong></p><p>Flood early warning systems (FEWS) can reduce casualties and economic losses (UNEP, 2012). The EC Horizon 2020 project FANFAR (www.fanfar.eu) aims to co-develop a FEWS in West Africa together with stakeholders, predicting streamflow and return period threshold exceedance (Andersson et al., 2020). A Multi-Criteria Decision Analysis (MCDA) indicated, that stakeholders find information accuracy especially important, among a broad set of fundamental objectives (Lienert et al., 2020). Social media have the potential to support accuracy assessment by detecting flood events (Lorini et al., 2019; de Bruijn et al., 2019) due to their large spatial coverage (Restrepo-Estrada et al., 2018). We investigated the potential of social media to assess FANFAR forecast accuracy.</p><p> </p><p><strong>Research Approach</strong></p><p>FANFAR forecasts are based on HYPE, which is a semi-distributed land-cover and sub-catchment based hydrological model (Arheimer et al., 2020). We lumped the forecasted flood risk (FFR) on a country scale and compared it to flood events detected on Twitter, using an algorithm (FEDA) developed by de Bruijn et al. (2019). FEDA detects flood-related tweet bursts based on regionally and temporally adjusted thresholds (de Bruijn et al., 2019). We compared FEDA detected events with floods from the disaster database EM-DAT (https://www.emdat.be/), to find if tweets indicate flooding. We also compared FEDA to the lumped FFR to identify false positives (FP), false negatives (FN), and true positives (TP), from which we deduced the probability of detection (POD) and false alarm rate (FAR). We further calculated the correlation of single flood-related tweets with the lumped FFR and investigated seasonality, lag, and the influence of rainfall.</p><p> </p><p><strong>Findings</strong></p><p>The detailed findings are described in Hohmann (2021). FEDA (i.e., tweets) and EM-DAT events (i.e., floods) mostly occurred in the same period. However, FEDA detected shorter and more frequent events than EM-DAT. In the Upper Niger, POD<sub>FEDA</sub> and FAR<sub>FEDA</sub> (deduced from FEDA) were of similar order of magnitude as the POD<sub>S</sub> and FAR<sub>S</sub> (deduced from streamflow) but were different in the Lower Niger region. This suggests that tweets can be employed additionally to e.g. streamflow timeseries as a complementary way to evaluate accuracy. Correlation analysis between single flood-related tweets and the lumped FFR showed no relationship. We also did not find a systematic influence of seasonality or a lagged response between tweets and FFR. The correlation coefficients between tweets and rainfall ranged from 0.1-0.9, but were mostly non-significant. This suggests that a performance assessment based on single tweets is not (yet) adequate. Also, since FEDA does not differentiate between pluvial and fluvial floods, it is less suited to assess the accuracy of FANFAR. Our findings suggest the need for inclusion of other factors into the performance assessment of FEWSs, such as regional thresholds to identify TP, FP, and FN. Also, rainfall causing pluvial flooding must be considered. Finally, our approach is limited to Twitter. Further research should assess the potential of e.g. Facebook to be included in FEWS performance assessment. The question whether social media, FEWSs, or EM-DAT are correct remains, and is in our opinion best addressed by employing multiple data sources.</p>

Toward customer-centric mobile phone reverse logistics: using the DEMATEL approach and social media data

Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sajjad Shokouhyar ◽  
Amirhosein Dehkhodaei ◽  
Bahar Amiri
Keyword(s):  
Social Media ◽  
Mobile Phone ◽  
Reverse Logistics ◽  
Product Life Cycle ◽  
High Efficiency ◽  
Threshold Value ◽  
Decision Makers ◽  
Special Focus ◽  
Content Type ◽  
Cause And Effect

PurposeRecently, reverse logistics (RL) has become more prominent due to growing environmental concerns, social responsibility, competitive advantages and high efficiency by customers because of expansion of product selection and shorter product life cycle. However, effective implementation of RL results in some direct advantages, the most important of which is winning customer satisfaction that is vital to a firm's success. Therefore, paying attention to customer feedback in supply chain (SC) and logistics processes has recently increased, so manufacturers have decided to transform their RL into customer-centric RL. Hence, this paper aims to identify the features of a mobile phone which affect consumers’ purchasing behavior and to analyze the causality and prominence relations among them that can help decision-makers, policy planners and managers of organizations to develop a framework for customer-centric RL. These features are studied based on analysis of product review sites. This paper's special focus is on social media (SM) data (Twitter) in an attempt to help the decision-making process in RL through a big data analysis approach.Design/methodology/approachThis paper deals with identifying mobile phone features that affect consumer's mobile phone purchasing decisions. Using the DEMATEL approach and using experts' insights, a cause and effect relationship diagram was generated through which the effect of features was analyzed.FindingsEighteen features were categorized in terms of cause and effect, and the interrelationships of features were also analyzed. The threshold value is calculated as 0.023, and the values lower than that were eliminated to obtain the digraph. F6 (camera), F13 (price) and F5 (chip) are the most prominent features based on their prominent score. It was also found that the F5 (chip) has the highest driving power (1.228) and acts as a causal feature to influence other features.Originality/valueThe focus of this article is on SM data (Twitter), so that experts can understand the interaction between mobile phone features that affect consumer's decision on mobile phone purchasing by using the results. This study investigates the degree of influence of features on each other and categorizes the features into cause and effect groups. This study is also intended to help organizational decision-makers move toward a reverse customer SC.

Algorithm for Automated Generation of a Training Sample for Solving the Problem of Determining Semantic Similarity between a Pair of Keywords using Machine Learning Methods

2021 ◽  
Vol 12 (6) ◽  
pp. 283-294
Author(s):  
K. V. Lunev ◽  
Keyword(s):  
Machine Learning ◽  
Semantic Similarity ◽  
Training Sample ◽  
Subject Area ◽  
Training Dataset ◽  
Training Set ◽  
Automated Generation ◽  
Machine Learning Methods ◽  
Subjective Value ◽  
The Subject

Currently, machine learning is an effective approach to solving many problems of information-analytical systems. To use such approaches, a training set of examples is required. Collecting a training dataset is usually a time-consuming process. Its implementation requires the participation of several experts in the subject area for which the training set is collected. Moreover, for some tasks, including the task of determining the semantic similarity of keyword pairs, it is difficult even to correctly draw up instructions for experts to adequately evaluate the test examples. The reason for such difficulties is that semantic similarity is a subjective value and strongly depends on the scope, context, person, and task. The article presents the results of research on the search for models, algorithms and software tools for the automated formation of objects of the training sample in the problem of determining the semantic similarity of a pair of words. In addition, models built on an automated training sample allow us to solve not only the problem of determining semantic similarity, but also an arbitrary problem of classifying edges of a graph. The methods used in this paper are based on graph theory algorithms.

Youth Participation in Politics

2019 ◽  
pp. 54-78 ◽  
Author(s):  
Sam Phiri
Keyword(s):  
Public Policy ◽  
Social Media ◽  
University Students ◽  
Survey Design ◽  
Representative Democracy ◽  
Decision Makers ◽  
Youth Participation ◽  
Social Media Platforms ◽  
Public Policy Decisions ◽  
Descriptive Survey

This chapter explores the manner in which Zambian university students engage with public policy decisions which are of immediate and future interest to them. It observes that the youths may have little faith in representative democracy and instead are utilizing social media platforms to directly engage with decision-makers and publics, and thus subverting the essence of the authority of parliament. The study uses descriptive survey design and the methodology of “Briscolage” to capture and scrutinize two politically charged cases, and concludes that the youth globally may be challenging liberalism and in that way fashioning a new narrative entrenched in postmodernism.

Sign in / Sign up

Export Citation Format

Share Document