scholarly journals Moderating with the Mob: Evaluating the Efficacy of Real-Time Crowdsourced Fact-Checking

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
William Godel ◽  
Zeve Sanderson ◽  
Kevin Aslett ◽  
Jonathan Nagler ◽  
Richard Bonneau ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Significant Variation ◽  
Political Knowledge ◽  
Third Party ◽  
News Stories ◽  
Social Media Platforms ◽  
Fact Checking ◽  
False News ◽  
Wisdom Of The Crowds

Reducing the spread of false news remains a challenge for social media platforms, as the current strategy of using third-party fact- checkers lacks the capacity to address both the scale and speed of misinformation diffusion. Research on the “wisdom of the crowds” suggests one possible solution: aggregating the evaluations of ordinary users to assess the veracity of information. In this study, we investigate the effectiveness of a scalable model for real-time crowdsourced fact-checking. We select 135 popular news stories and have them evaluated by both ordinary individuals and professional fact-checkers within 72 hours of publication, producing 12,883 individual evaluations. Although we find that machine learning-based models using the crowd perform better at identifying false news than simple aggregation rules, our results suggest that neither approach is able to perform at the level of professional fact-checkers. Additionally, both methods perform best when using evaluations only from survey respondents with high political knowledge, suggesting reason for caution for crowdsourced models that rely on a representative sample of the population. Overall, our analyses reveal that while crowd-based systems provide some information on news quality, they are nonetheless limited—and have significant variation—in their ability to identify false news.

scholarly journals Intentional or inadvertent fake news sharing? Fact-checking warnings and users’ interaction with social media content

2020 ◽  
Author(s):  
Alberto Ardèvol-Abreu ◽  
Patricia Delponti ◽  
Carmen Rodríguez-Wangüemert
Keyword(s):  
Social Media ◽  
Online Survey ◽  
Media Content ◽  
Fake News ◽  
Negative Effects ◽  
News Stories ◽  
Social Media Platforms ◽  
Fact Checking ◽  
False News ◽  
News Sharing

The main social media platforms have been implementing strategies to minimize fake news dissemination. These include identifying, labeling, and penalizing –via news feed ranking algorithms– fake publications. Part of the rationale behind this approach is that the negative effects of fake content arise only when social media users are deceived. Once debunked, fake posts and news stories should therefore become harmless. Unfortunately, the literature shows that the effects of misinformation are more complex and tend to persist and even backfire after correction. Furthermore, we still do not know much about how social media users evaluate content that has been fact-checked and flagged as false. More worryingly, previous findings suggest that some people may intentionally share made up news on social media, although their motivations are not fully explained. To better understand users’ interaction with social media content identified or recognized as false, we analyze qualitative and quantitative data from five focus groups and a sub-national online survey (N = 350). Findings suggest that the label of ‘false news’ plays a role –although not necessarily central– in social media users’ evaluation of the content and their decision (not) to share it. Some participants showed distrust in fact-checkers and lack of knowledge about the fact-checking process. We also found that fake news sharing is a two-dimensional phenomenon that includes intentional and unintentional behaviors. We discuss some of the reasons why some of social media users may choose to distribute fake news content intentionally.

Spiritualism and the Resurgence of Fake News

2020 ◽  
pp. 222-237
Author(s):  
Kristy A. Hesketh
Keyword(s):  
Social Media ◽  
Mass Media ◽  
Fake News ◽  
News Stories ◽  
News Reports ◽  
The World ◽  
Spirit World ◽  
Social Media Platforms ◽  
Media Platform ◽  
False News

This chapter explores the Spiritualist movement and its rapid growth due to the formation of mass media and compares these events with the current rise of fake news in the mass media. The technology of cheaper publications created a media platform that featured stories about Spiritualist mediums and communications with the spirit world. These articles were published in newspapers next to regular news creating a blurred line between real and hoax news stories. Laws were later created to address instances of fraud that occurred in the medium industry. Today, social media platforms provide a similar vessel for the spread of fake news. Online fake news is published alongside legitimate news reports leaving readers unable to differentiate between real and fake articles. Around the world countries are actioning initiatives to address the proliferation of false news to prevent the spread of misinformation. This chapter compares the parallels between these events, how hoaxes and fake news begin and spread, and examines the measures governments are taking to curb the growth of misinformation.

Survey on Fake News or Truth - Rumours Detection using Machine Learning

2021 ◽  
Vol 7 (3) ◽  
Author(s):  
Kalyani Deore ◽  
Leena Gaikwad ◽  
Rohit Dhamne ◽  
Vishal Agale ◽  
T. Bhaskar
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Machine Learning Algorithms ◽  
Modern World ◽  
Fake News ◽  
Misleading Information ◽  
Original Source ◽  
News Stories ◽  
False News ◽  
Communication Methods

This study is to help readers to understand detection of fake news using machine learning. The main purpose of the planned system is to build an application which identifies fake news stories from a bunch of news stories to make people aware of fake news rumours. With the help of machine learning algorithms, we can detect and separate out the fake news. Nowadays, it is become harder to identify the original source of news stories, like looking for a needle in a haystack. In the modern world, news is a kind of communication that keeps us up to date on the latest events, topics, and people in the wider globe. A society relies on news for a variety of reasons, the most important of which is informing its members about events taking on in and around them that might influence them. Oral and traditional media, as well as digital communication methods, altered videos, memes, unconfirmed marketing, and social media have all contributed to the spread of rumors. As nowadays many people use social media in many cases people get wrong and misleading information and people share those stories without verifying whether it is real or fake news stories. Spreading false information on social media has become a major problem these days. That is why we need a system that can tell us whether something is false news or not. Applications are: 1. Fake news may be detected on social media using this approach. 2. The system can be used to help news channels to broadcast only real and classified news. 3. Users can easily detect and eliminate fake articles that contain misinformation intended to mislead readers.

Information Extraction From Social Media for Epidemic Models

2021 ◽  
pp. 125-139
Author(s):  
Tariq Soussan ◽  
Marcello Trovati
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Social Media ◽  
Real Time ◽  
General Information ◽  
Mining Machine ◽  
Time Data ◽  
Real Time Data ◽  
Social Media Platforms ◽  
Modelling Techniques

Social media platforms are widely used to share opinions, facts, and real-time general information on specific events. This chapter will focus on discussing and presenting data analytics approaches which combine a variety of techniques based on text mining, machine learning, network analysis, and mathematical modelling to assess real-time data extracted from social media and other suitable data related to pandemic outbreaks. The use of real-time insights regarding pandemic outbreaks provides a valuable tool to inform and validate existing modelling techniques and methods. Furthermore, this would also support the discovering process of actionable information to facilitate the decision-making process by enhancing the most informed and appropriate decision, based on the available data. The chapter will also focus on the visualisation and usability of the insight identified during the process to address a non-technical audience.

Creating adaptive predictions for packaging-critical quality parameters using advanced analytics and machine learning

TAPPI Journal ◽  
2019 ◽  
Vol 18 (11) ◽  
pp. 679-689
Author(s):  
CYDNEY RECHTIN ◽  
CHITTA RANJAN ◽  
ANTHONY LEWIS ◽  
BETH ANN ZARKO
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Predictive Analytics ◽  
Paper Industry ◽  
Quality Parameters ◽  
Fast Change ◽  
The Face ◽  
Model Tuning ◽  
Reducing Costs ◽  
Time Critical

Packaging manufacturers are challenged to achieve consistent strength targets and maximize production while reducing costs through smarter fiber utilization, chemical optimization, energy reduction, and more. With innovative instrumentation readily accessible, mills are collecting vast amounts of data that provide them with ever increasing visibility into their processes. Turning this visibility into actionable insight is key to successfully exceeding customer expectations and reducing costs. Predictive analytics supported by machine learning can provide real-time quality measures that remain robust and accurate in the face of changing machine conditions. These adaptive quality “soft sensors” allow for more informed, on-the-fly process changes; fast change detection; and process control optimization without requiring periodic model tuning. The use of predictive modeling in the paper industry has increased in recent years; however, little attention has been given to packaging finished quality. The use of machine learning to maintain prediction relevancy under everchanging machine conditions is novel. In this paper, we demonstrate the process of establishing real-time, adaptive quality predictions in an industry focused on reel-to-reel quality control, and we discuss the value created through the availability and use of real-time critical quality.

Speech Organ Contour Extraction Using Real-Time MRI and Machine Learning Method

2019 ◽  
Author(s):  
Hironori Takemoto ◽  
Tsubasa Goto ◽  
Yuya Hagihara ◽  
Sayaka Hamanaka ◽  
Tatsuya Kitamura ◽  
...  
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Machine Learning Method ◽  
Learning Method ◽  
Contour Extraction

scholarly journals Deep Transfer Learning Based Intrusion Detection System for Electric Vehicular Networks

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4736
Author(s):  
Sk. Tanzir Mehedi ◽  
Adnan Anwar ◽  
Ziaur Rahman ◽  
Kawsar Ahmed
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Intrusion Detection ◽  
Real Time ◽  
Transfer Learning ◽  
Security Requirements ◽  
Detection Accuracy ◽  
Area Network ◽  
Complex Data ◽  
Network Intrusion

The Controller Area Network (CAN) bus works as an important protocol in the real-time In-Vehicle Network (IVN) systems for its simple, suitable, and robust architecture. The risk of IVN devices has still been insecure and vulnerable due to the complex data-intensive architectures which greatly increase the accessibility to unauthorized networks and the possibility of various types of cyberattacks. Therefore, the detection of cyberattacks in IVN devices has become a growing interest. With the rapid development of IVNs and evolving threat types, the traditional machine learning-based IDS has to update to cope with the security requirements of the current environment. Nowadays, the progression of deep learning, deep transfer learning, and its impactful outcome in several areas has guided as an effective solution for network intrusion detection. This manuscript proposes a deep transfer learning-based IDS model for IVN along with improved performance in comparison to several other existing models. The unique contributions include effective attribute selection which is best suited to identify malicious CAN messages and accurately detect the normal and abnormal activities, designing a deep transfer learning-based LeNet model, and evaluating considering real-world data. To this end, an extensive experimental performance evaluation has been conducted. The architecture along with empirical analyses shows that the proposed IDS greatly improves the detection accuracy over the mainstream machine learning, deep learning, and benchmark deep transfer learning models and has demonstrated better performance for real-time IVN security.

Sign in / Sign up

Export Citation Format

Share Document