Search results for: fake reviews

Authors: Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Abstract:

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.

Keywords: fake news detection, natural language processing, machine learning, classification techniques.

Procedia PDF Downloads 129

Authors: Mohammadali Tavakoli, Atefeh Heydari, Zuriati Ismail, Naomie Salim

Abstract:

With the increasing number of people reviewing products online in recent years, opinion sharing websites has become the most important source of customers’ opinions. Unfortunately, spammers generate and post fake reviews in order to promote or demote brands and mislead potential customers. These are notably destructive not only for potential customers but also for business holders and manufacturers. However, research in this area is not adequate, and many critical problems related to spam detection have not been solved to date. To provide green researchers in the domain with a great aid, in this paper, we have attempted to create a high-quality framework to make a clear vision on review spam-detection methods. In addition, this report contains a comprehensive collection of detection metrics used in proposed spam-detection approaches. These metrics are extremely applicable for developing novel detection methods.

Keywords: fake reviews, feature collection, opinion spam, spam detection

Procedia PDF Downloads 381

Authors: Ida Shafinaz Mohamed Kamil, Mohd Dahlan Abdul Malek

Abstract:

Today, the whole world is facing a catastrophe called the novel coronavirus disease known as COVID-19. As of October 2021, it has been reported that more than 248 million cases and 5 million deaths have been recorded worldwide. In Malaysia, 2,466,663 cases were reported, with 28,876 deaths recorded on 30 October 2021. Unfortunately, the world is not only facing the COVID-19 pandemic but the COVID-19 infodemic as well, where fake news about COVID-19 disease is spreading faster and more widely than from the virus itself. The spread of fake news is amplified through various social media platforms, which is causing concern among the community. The uncertainty in understanding what fake news really is has caused difficulties and challenges in providing a solution to the hazards that it creates. This article discusses what constitutes fake news and examines the current legal framework put in place to combat fake news in Malaysia. Employing a doctrinal research methodology, this article thoroughly analyzes the relevant legal provisions under the Communications and Multimedia Act 1998, the Penal Code and the Emergency (Essential Powers) Ordinance (No.2) 2021, which came into force on 12 March 2021 as well as related case laws, for offenses and punishments with regards to fake news. The findings from the analysis indicate that there is still room for improvement in regulating fake news, in particular concerning COVID-19.

Keywords: fake news, legal pespective, covid 19, pendemic

Procedia PDF Downloads 52

Authors: Job Bapyibi Guyson, Bangripa Kefas

Abstract:

The advent of social media has no doubt provided platforms that facilitate the spread of fake news. The devastating impact of this does not only end with the prevalence of rumours and propaganda but also poses potential impact on individuals’ mental well-being. Therefore, this study on examining the impact of fake news on the mental health of residents in Jos metropolis among others interrogates the impact of exposure to fake news on residents' mental health. Anchored on the Cultivation Theory, the study adopted quantitative method and surveyed two the opinions of hundred (200) social media users in Jos metropolis using purposive sampling technique. The findings reveal that a significant majority of respondents perceive fake news as highly prevalent on social media, with associated feelings of anxiety and stress. The majority of the respondents express confidence in identifying fake news, though a notable proportion lacks such confidence. Strategies for managing the mental impact of encountering fake news include ignoring it, fact checking, discussing with others, reporting to platforms, and seeking professional support. Based on these insights, recommendations were proposed to address the challenges posed by fake news. These include promoting media literacy, integrating fact-checking tools, adjusting algorithms and fostering digital well-being features among others.

Keywords: fake news, mental health, social media, impact

Procedia PDF Downloads 6

Authors: Tae-Uk Yun, Pullip Chung, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection using machine learning techniques over the past years. But, there have been no prior studies proposed an automated fake news detection method for Korean news to our best knowledge. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (topic modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as logistic regression, backpropagation network, support vector machine, and deep neural network can be applied. To validate the effectiveness of the proposed method, we collected about 200 short Korean news from Seoul National University’s FactCheck. which provides with detailed analysis reports from 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

Keywords: fake news detection, Korean news, machine learning, text mining

Procedia PDF Downloads 241

Authors: Agrinë Baraku

Abstract:

This paper focuses on the convergence of the internet, fake news, and democracy. This paper will examine the convergence of these concepts, the tenets of democracy which are affected by the ever-increasing exposure to fake news, and whether the impact strengthens or can further weaken countries with fragile democracies. To demonstrate the convergence and the impact and to further the discussion about this topic, the case of Kosovo is explored. Its position in the Western Balkans makes it even more susceptible to the pressure stemming from geopolitical interests, which intersect with the generation of fake news by different international actors. Domestically, through data generated by Kantar (Index) Kosova Longitudinal Study on Media Measurement Survey (MMS), which focused on media viewership, the trend among Kosovar citizens is traced and then inserted into a bigger landscape, which is compounded by tenuous circumstances and challenges that Kosovo faces. Attention will be paid to what this can tell about where Kosovo currently is and the possibilities of what can be done regarding the phenomenon that is taking place.

Keywords: democracy, disinformation, internet, social media, fake news

Procedia PDF Downloads 65

Authors: Jaejun Jong

Abstract:

Fake news has recently become a serious international problem. Therefore, researchers and policymakers worldwide have sought to understand fake news and develop strategies to combat it. This study consists of two primary parts: (1) a literature review of how surveys were used to understand fake news and identify problems caused by fake news, and (2) a discussion of how surveys were used to fight back against fake news in educational settings. This second section specifically analyzes surveys used to evaluate a South Korean elementary school program designed to improve students’ metacognition and critical thinking. This section seeks to identify potential problems that may occur in the elementary school setting. The literature review shows that surveys can help people to understand fake news based on its traits rather than its definition due to the lack of agreement on the definition of fake news. The literature review also shows that people are not good at identifying fake news or evaluating their own ability to identify fake news; indeed, they are more likely to share information that aligns with their previous beliefs. In addition, the elementary school survey data shows that there may be substantial errors in the program evaluation process, likely caused by processing errors or the survey procedure, though the exact cause is not specified. Such a significant error in evaluating the effects of the educational program prevents teachers from making proper decisions and accurately evaluating the program. Therefore, identifying the source of such errors would improve the overall quality of education, which would benefit both teachers and students.

Keywords: critical thinking, elementary education, program evaluation, survey

Procedia PDF Downloads 68

Authors: Joseph Uzuazomaro Oju

Abstract:

The ease at which manipulated media can be created, and the increasing difficulty in identifying fake media makes it a great threat. Most of the applications used for the creation of these high-quality fake videos and images are built with deep learning. Hence, the use of deep learning in creating a detection mechanism cannot be overemphasized. Any successful fake media that is being detected before it reached the populace will save people from the self-doubt of either a content is genuine or fake and will ensure the credibility of videos and images. The methodology introduced in this paper approaches the manipulated media detection challenge using a combo of VGG-19 and a deep capsule network. In the case of videos, they are converted into frames, which, in turn, are resized and cropped to the face region. These preprocessed images/videos are fed to the VGG-19 network to extract the latent features. The extracted latent features are inputted into a deep capsule network enhanced with a 3D -convolution dynamic routing agreement. The 3D –convolution dynamic routing agreement algorithm helps to reduce the linkages between capsules networks. Thereby limiting the poor learning shortcoming of multiple capsule network layers. The resultant output from the deep capsule network will indicate a media to be either genuine or fake.

Keywords: deep capsule network, dynamic routing, fake media detection, manipulated media

Procedia PDF Downloads 96

Authors: AnjalI A. Prasad

Abstract:

Nowadays, social media played an important role in spreading misinformation or fake news. This study analyzes the fake news related to the COVID-19 pandemic spread in social media. This paper aims at evaluating and comparing different approaches that are used to mitigate this issue, including popular deep learning approaches, such as CNN, RNN, LSTM, and BERT algorithm for classification. To evaluate models’ performance, we used accuracy, precision, recall, and F1-score as the evaluation metrics. And finally, compare which algorithm shows better result among the four algorithms.

Keywords: BERT, CNN, LSTM, RNN

Procedia PDF Downloads 169

Authors: Marion Billard

Abstract:

This paper will focus on the question of the real relationship between young people and fake news. Fake news is one of today’s main issues in the world of information and communication. Social media and its democratization helped to spread false information. According to traditional beliefs, young people are more inclined to believe what they read through social media. But, the individuals concerned, think that they are more inclined to make a distinction between real and fake news. This phenomenon is due to their use of the internet and social media from an early age. During the 2016 and 2017 French and American presidential campaigns, the term fake news was in the mouth of the entire world and became a real issue in the field of information. While young people were informing themselves with newspapers or television until the beginning of the ’90s, Gen Z (meaning people born between 1997 and 2010), has always been immersed in this world of fast communication. They know how to use social media from a young age and the internet has no secret for them. Today, despite the sporadic use of traditional media, young people tend to turn to their smartphones and social networks such as Instagram or Twitter to stay abreast of the latest news. The growth of social media information led to an “ambient journalism”, giving access to an endless quantity of information. Waking up in the morning, young people will see little posts with short texts supplying the essential of the news, without, for the most, many details. As a result, impressionable people are not able to do a distinction between real media, and “junk news” or Fake News. This massive use of social media is probably explained by the inability of the youngsters to find connections between the communication of the traditional media and what they are living. The question arises if this over-confidence of the young people in their ability to distinguish between accurate and fake news would not make it more difficult for them to examine critically the information. Their relationship with media and fake news is more complex than popular opinion. Today’s young people are not the master in the quest for information, nor inherently the most impressionable public on social media.

Keywords: fake news, youngsters, social media, information, generation

Procedia PDF Downloads 131

Authors: Chaima Babi, Said Gadri

Abstract:

The rapid increase in fake news continues to grow at a very fast rate; this requires implementing efficient techniques that allow testing the re-liability of online content. For that, the current research strives to illuminate the fake news problem using deep learning DL and machine learning ML ap-proaches. We have developed the traditional LSTM (Long short-term memory), and the bidirectional BiLSTM model. A such process is to perform a training task on almost of samples of the dataset, validate the model on a subset called the test set to provide an unbiased evaluation of the final model fit on the training dataset, then compute the accuracy of detecting classifica-tion and comparing the results. For the programming stage, we used Tensor-Flow and Keras libraries on Python to support Graphical Processing Units (GPUs) that are being used for developing deep learning applications.

Keywords: machine learning, deep learning, natural language, fake news, Bi-LSTM, LSTM, multiclass classification

Procedia PDF Downloads 42

Authors: Gloria Ebere Amadi, Emeka Promise Ugwunwotti

Abstract:

The study was carried out to determine the strategies for managing fake news for sustainable democracy in Enugu State, Nigeria. Two research questions and two null hypotheses guided the study. A survey research design was used for the study. The population for the study consisted of 100 respondents (from Enugu state House of Assembly). Of the entire population, 24 elected law makers and 76 staff were used; hence there was no sampling since the population was manageable. A 28-item structured questionnaire developed by the researcher was used for data collection. The instrument entitled Managing Fake News Questionnaire (MFNQ) was validated by three experts, two from the Department of Computer Science and one from the Department of Maths and Statistics, all from Enugu State University of Science and Technology. Cronbach Alpha was used to determine the reliability coefficient of the two sections of the instrument, and they are 0.67 and 0.82, while the reliability coefficient of the whole instrument gave a value of 0.81. Mean with standard deviation was used to answer research questions, while the null hypotheses at 0.5 level of significance at 98 degrees of freedom were tested with a t-test. The findings of the study revealed that the respondents agreed that government and citizens-related strategies improve the management of fake news for sustainable democracy in Enugu State. Again, there was no significant difference between the mean response of the lawmakers and staff on government and citizens-related strategies for managing fake news for sustainable democracy in Enugu State. Based on the findings, it was recommended, among others, that there should be regular workshops on the management of fake news for citizens.

Keywords: fake news, sustainability, democracy, management

Procedia PDF Downloads 42

Authors: Yulan Wu

Abstract:

With the rapid development of social media, the issue of fake news has gained considerable prominence, drawing the attention of both the public and governments. The widespread dissemination of false information poses a tangible threat across multiple domains of society, including politics, economy, and health. However, much research has concentrated on supervised training models within specific domains, their effectiveness diminishes when applied to identify fake news across multiple domains. To solve this problem, some approaches based on domain labels have been proposed. By segmenting news to their specific area in advance, judges in the corresponding field may be more accurate on fake news. However, these approaches disregard the fact that news records can pertain to multiple domains, resulting in a significant loss of valuable information. In addition, the datasets used for training must all be domain-labeled, which creates unnecessary complexity. To solve these problems, an unsupervised domain knowledge discovery framework for fake news detection is proposed. Firstly, to effectively retain the multidomain knowledge of the text, a low-dimensional vector for each news text to capture domain embeddings is generated. Subsequently, a feature extraction module utilizing the unsupervisedly discovered domain embeddings is used to extract the comprehensive features of news. Finally, a classifier is employed to determine the authenticity of the news. To verify the proposed framework, a test is conducted on the existing widely used datasets, and the experimental results demonstrate that this method is able to improve the detection performance for fake news across multiple domains. Moreover, even in datasets that lack domain labels, this method can still effectively transfer domain knowledge, which can educe the time consumed by tagging without sacrificing the detection accuracy.

Keywords: fake news, deep learning, natural language processing, multiple domains

Procedia PDF Downloads 47

Authors: Ahmed ElAzab, Amira M. Idrees, Mahmoud A. Mahmoud, Hesham Hefny

Abstract:

Social networking sites such as Twitter and Facebook attracts over 500 million users across the world, for those users, their social life, even their practical life, has become interrelated. Their interaction with social networking has affected their life forever. Accordingly, social networking sites have become among the main channels that are responsible for vast dissemination of different kinds of information during real time events. This popularity in Social networking has led to different problems including the possibility of exposing incorrect information to their users through fake accounts which results to the spread of malicious content during life events. This situation can result to a huge damage in the real world to the society in general including citizens, business entities, and others. In this paper, we present a classification method for detecting fake accounts on Twitter. The study determines the minimized set of the main factors that influence the detection of the fake accounts on Twitter, then the determined factors have been applied using different classification techniques, a comparison of the results for these techniques has been performed and the most accurate algorithm is selected according to the accuracy of the results. The study has been compared with different recent research in the same area, this comparison has proved the accuracy of the proposed study. We claim that this study can be continuously applied on Twitter social network to automatically detect the fake accounts, moreover, the study can be applied on different Social network sites such as Facebook with minor changes according to the nature of the social network which are discussed in this paper.

Keywords: fake accounts detection, classification algorithms, twitter accounts analysis, features based techniques

Procedia PDF Downloads 366

Authors: Yulan Wu

Abstract:

The spread of fake news on social media has posed significant societal harm to the public and the nation, with its threats spanning various domains, including politics, economics, health, and more. News on social media often covers multiple domains, and existing models studied by researchers and relevant organizations often perform well on datasets from a single domain. However, when these methods are applied to social platforms with news spanning multiple domains, their performance significantly deteriorates. Existing research has attempted to enhance the detection performance of multi-domain datasets by adding single-domain labels to the data. However, these methods overlook the fact that a news article typically belongs to multiple domains, leading to the loss of domain knowledge information contained within the news text. To address this issue, research has found that news records in different domains often use different vocabularies to describe their content. In this paper, we propose a fake news detection framework that combines domain knowledge and expert knowledge. Firstly, it utilizes an unsupervised domain discovery module to generate a low-dimensional vector for each news article, representing domain embeddings, which can retain multi-domain knowledge of the news content. Then, a feature extraction module uses the domain embeddings discovered through unsupervised domain knowledge to guide multiple experts in extracting news knowledge for the total feature representation. Finally, a classifier is used to determine whether the news is fake or not. Experiments show that this approach can improve multi-domain fake news detection performance while reducing the cost of manually labeling domain labels.

Keywords: fake news, deep learning, natural language processing, multiple domains

Procedia PDF Downloads 33

Authors: Laura Irimies, Cosmin Irimies

Abstract:

The public space all over the world is currently confronted with the aggressive assault of fake news that have lately impacted public agenda setting, collective decisions and social attitudes. Top leaders constantly call out most mainstream news as “fake news” and the public opinion get more confused. "Fake news" are generally defined as false, often sensational, information disseminated under the guise of news reporting and has been declared the word of the year 2017 by Collins Dictionary and it also has been one of the most debated socio-political topics of recent years. Websites which, deliberately or not, publish misleading information are often shared on social media where they essentially increase their reach and influence. According to international reports, the exposure to fake news is an undeniable reality all over the world as the exposure to completely invented information goes up to the 31 percent in the US, and it is even bigger in Eastern Europe countries, such as Hungary (42%) and Romania (38%) or in Mediterranean countries, such as Greece (44%) or Turkey (49%), and lower in Northern and Western Europe countries – Germany (9%), Denmark (9%) or Holland (10%). While the study of fake news (mechanism and effects) is still in its infancy, it has become truly relevant as the phenomenon seems to have a growing impact on democratic systems. Studies conducted by the European Commission show that 83% of respondents out of a total of 26,576 interviewees consider the existence of news that misrepresent reality as a threat for democracy. Studies recently conducted at Arizona State University show that people with higher education can more easily spot fake headlines, but over 30 percent of them can still be trapped by fake information. If we were to refer only to some of the most recent situations in Romania, fake news issues and hidden agenda suspicions related to the massive and extremely violent public demonstrations held on August 10th, 2018 with a strong participation of the Romanian diaspora have been massively reflected by the international media and generated serious debates within the European Commission. Considering the above framework, the study raises four main research questions: 1. Is fake news a problem or just a natural consequence of mainstream media decline and the abundance of sources of information? 2. What are the implications for democracy? 3. Can fake news be controlled without restricting fundamental human rights? 4. How could the public be properly educated to detect fake news? The research uses mostly qualitative but also quantitative methods, content analysis of studies, websites and media content, official reports and interviews. The study will prove the real threat fake news represent and also the need for proper media literacy education and will draw basic guidelines for developing a new and essential skill: that of detecting fake in news in a society overwhelmed by sources of information that constantly roll massive amounts of information increasing the risk of misinformation and leading to inadequate public decisions that could affect democratic stability.

Keywords: agenda setting democracy, fake news, journalism, media literacy

Procedia PDF Downloads 95

Authors: Aron Miranda Burgos, Ergon Cugler de Moraes Silva

Abstract:

In the present article, it is observed that the constant advancement of issues related to misinformation impacts the guarantee of the public policy cycle. Thus, it is found that the dissemination of false information has a direct influence on each of the component stages of this cycle. Therefore, in order to maintain scientific and theoretical credibility in the qualitative analysis process, it was necessary to logically interpose the concepts of firehosing of falsehood, fake news, public policy cycle, as well as using the epistemological and pragmatic mechanism at the intersection of such academic concepts, such as the scientific method. It was found, through the analysis of official documents and public notes, how the multiple theoretical perspectives evidence the commitment of the provision and elaboration of public policies, verifying the way in which the fake news impact each part of the process in this atmosphere.

Keywords: firehosing of falsehood, governance, misinformation, post-truth

Procedia PDF Downloads 106

Authors: Sarif Ullah Patwary, Matthew Heinrich, Brandon Payne

Abstract:

The ubiquity of web 2.0 platforms, in the form of wikis, social media (e.g., Facebook, Twitter, etc.) and online review portals (e.g., Yelp), helps shape today’s apparel consumers’ purchasing decision. Online reviews play important role towards consumers’ apparel purchase decision. Each of the consumer reviews carries a sentiment (positive, negative or neutral) towards products. Commercially, apparel brands and retailers analyze sentiment of this massive amount of consumer review data to update their inventory and bring new products in the market. The purpose of this study is to analyze consumer reviews of selected apparel stores with a view to understand, 1) the difference of sentiment expressed through men’s and woman’s text reviews, 2) the difference of sentiment expressed through men’s and woman’s star-based reviews, and 3) the difference of sentiment between star-based reviews and text-based reviews. A total of 9,363 reviews (1,713 men and 7,650 women) were collected using Yelp Dataset Challenge. Sentiment analysis of collected reviews was carried out in two dimensions: star-based reviews and text-based reviews. Sentiment towards apparel stores expressed through star-based reviews was deemed: 1) positive for 3 or 4 stars 2) negative for 1 or 2 stars and 3) neutral for 3 stars. Sentiment analysis of text-based reviews was carried out using Bing Liu dictionary. The analysis was conducted in IPyhton 5.0. Space. The sentiment analysis results revealed the percentage of positive text reviews by men (80%) and women (80%) were identical. Women reviewers (12%) provided more neutral (e.g., 3 out of 5 stars) star reviews than men (6%). Star-based reviews were more negative than the text-based reviews. In other words, while 80% men and women wrote positive reviews for the stores, less than 70% ended up giving 4 or 5 stars in those reviews. One of the key takeaways of the study is that star reviews provide slightly negative sentiment of the consumer reviews. Therefore, in order to understand sentiment towards apparel products, one might need to combine both star and text aspects of consumer reviews. This study used a specific dataset consisting of selected apparel stores from particular geographical locations (the information was not given for privacy concern). Future studies need to include more data from more stores and locations to generalize the findings of the study.

Keywords: apparel, consumer review, sentiment analysis, gender

Procedia PDF Downloads 134

Authors: Kasra Majbouri Yazdi, Adel Majbouri Yazdi, Saeid Khodayi, Jingyu Hou, Wanlei Zhou, Saeed Saedy

Abstract:

Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.

Keywords: clustering, fake news detection, feature selection, machine learning, social media, support vector machine

Procedia PDF Downloads 143

Authors: Yehjune Heo

Abstract:

Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.

Keywords: anti-spoofing, CNN, fingerprint recognition, GAN

Procedia PDF Downloads 158

Authors: Sekkal Nawel, Mahammed Nadir

Abstract:

The proliferation of online activities on Online Social Networks (OSNs) has captured significant user attention. However, this growth has been hindered by the emergence of fraudulent accounts that do not represent real individuals and violate privacy regulations within social network communities. Consequently, it is imperative to identify and remove these profiles to enhance the security of OSN users. In recent years, researchers have turned to machine learning (ML) to develop strategies and methods to tackle this issue. Numerous studies have been conducted in this field to compare various ML-based techniques. However, the existing literature still lacks a comprehensive examination, especially considering different OSN platforms. Additionally, the utilization of bio-inspired algorithms has been largely overlooked. Our study conducts an extensive comparison analysis of various fake profile detection techniques in online social networks. The results of our study indicate that supervised models, along with other machine learning techniques, as well as unsupervised models, are effective for detecting false profiles in social media. To achieve optimal results, we have incorporated six bio-inspired algorithms to enhance the performance of fake profile identification results.

Keywords: machine learning, bio-inspired algorithm, detection, fake profile, system, social network

Procedia PDF Downloads 32

Authors: Laura C. Solzbacher, Caja Thimm

Abstract:

Journalists worldwide have been confronted with a variety of ethical challenges over the last years. Because of massive changes in media technology and the public sphere, especially online journalism has trouble to uphold the fundamental values of journalism. In particular, the increasing amount of fake news and hate speech puts journalists under more and more pressure. In order to understand better how journalists judge this development and how they adapt in their daily work, a survey with journalists in Germany was carried out. 303 professional journalists participated in an online questionnaire. Results show that 65% underline that economic pressure grows and nearly the same number describe a change in the role of journalists in society. Furthermore, 61% agree that they put more time into research to secure their work against accusations of fabricating fake news. Interestingly, over 60% see a change in the role of journalists in society. The majority (85%) confirms that print journalism has to give way for online platforms and that the influence of social media for journalism grows (75%). Half of the surveyed advocate for more personalized public activism on part of journalists, such as appearance in talk shows and public talks. The results of the study will be discussed in light of the ongoing debate on ethical standards as a condition for a sustainable and trustworthy digital public sphere.

Keywords: ethics, fake news, journalism, public sphere

Procedia PDF Downloads 241

Authors: Yu Hung Chiang, Hei Chia Wang

Abstract:

Nowadays, tourism has become a part of life. Before reserving hotels, customers need some information, which the most important source is online reviews, about hotels to help them make decisions. Due to the dramatic growing of online reviews, it is impossible for tourists to read all reviews manually. Therefore, designing an automatic review analysis system, which summarizes reviews, is necessary for them. The main purpose of the system is to understand the opinion of reviews, which may be positive or negative. In other words, the system would analyze whether the customers who visited the hotel like it or not. Using sentiment analysis methods will help the system achieve the purpose. In sentiment analysis methods, the targets of opinion (here they are called the feature) should be recognized to clarify the polarity of the opinion because polarity of the opinion may be ambiguous. Hence, the study proposes an unsupervised method using Part-Of-Speech pattern and multi-lexicons sentiment analysis to summarize all reviews. We expect this method can help customers search what they want information as well as make decisions efficiently.

Keywords: text mining, sentiment analysis, product feature extraction, multi-lexicons

Procedia PDF Downloads 300

Authors: Jenna Barriault, Reeshma Haji

Abstract:

Online consumer behaviourand reliance on online reviews may be more pervasive than ever, andthis necessitates a better scientific understanding of the widespread phenomenon of online deception. The present research focuses on the understudied topic of deceiver’s distrust, where those who engage in deception later have less trust in others in the context of online restaurant reviews. The purpose was to examine deception and valence in online restaurant reviews and the effects they had on deceiver’s distrust. Undergraduate university students (N = 76) completed an online study where valence was uniquely manipulated by telling participants that either positive (or negative reviews) were influential and asking them to write a correspondingly valenced review. Deception was manipulated in the same task. Participants in the deception condition were asked to write an online restaurant review that was counter to their actual experience of the restaurant (negative review of a restaurant they liked, positive review of the restaurant they did not like). In the no deception condition, participants were asked to write a review that they actually liked or didn’t like (based on the valence condition to which they were randomly assigned). Participants’ trust was then assessed through various measures, includingfuture reliance on online reviews. There was a main effect of deception on reliance on online reviews. Consistent with deceiver’s distrust, those who deceived reported that they would rely less on online reviews. This study demonstrates that even when participants are induced to write a deceptive review, it can result in deceiver’s distrust, thereby lowering their trust in online reviews. If trust or reliance can be altered through deception in online reviews, people may start questioning the objectivity or true representation of a company based on such reviews. A primary implication is that people may reduce theirreliance upon online reviews if they know they are easily subject to manipulation. The findings of this study also contribute to the limited research regarding deceiver’s distrust in an online context, and further research is clarifying the specific conditions in which it is most likely to occur.

Keywords: deceiver’s distrust, deception, online reviews, trust, valence

Procedia PDF Downloads 87

Authors: Subhadeep Mandal, Sujoy Bhattacharya, Pabitra Mitra, Diya Guha Roy, Seema Bhattacharya

Abstract:

E-commerce firms allow customers to evaluate and review the things they buy as a positive or bad experience. The e-commerce transaction processes are made up of a variety of diverse organizations and activities that operate independently but are connected together to complete the transaction (from placing an order to the goods reaching the client). After a negative shopping experience, clients frequently disregard the critical assessment of these businesses and submit their feedback on an all-over basis, which benefits certain enterprises but is tedious for others. In this article, we solely dealt with negative reviews and attempted to distinguish between negative reviews where the e-commerce firm is explicitly blamed by customers for a bad purchasing experience and other negative reviews.

Keywords: e-commerce, online shopping, customer reviews, customer behaviour, text analytics, n-grams classification

Procedia PDF Downloads 219

Authors: Samaneh Nadali, Masrah Azrifah Azmi Murad

Abstract:

As a result of the growth of the web, people are able to express their views and opinions. They can now post reviews of products at merchant sites and express their views on almost anything in internet forums, discussion groups, and blogs. Therefore, the number of product reviews has grown rapidly. The large numbers of reviews make it difficult for manufacturers or businesses to automatically classify them into different semantic orientations (positive, negative, and neutral). For sentiment classification, most existing methods utilize a list of opinion words whereas this paper proposes a fuzzy approach for evaluating sentiments expressed in customer product reviews, to predict the strength levels (e.g. very weak, weak, moderate, strong and very strong) of customer product reviews by combinations of adjective, adverb and verb. The proposed fuzzy approach has been tested on eight benchmark datasets and obtained 74% accuracy, which leads to help the organization with a more clear understanding of customer's behavior in support of business planning process.

Keywords: fuzzy logic, customer product review, sentiment analysis

Procedia PDF Downloads 329

Authors: Atefeh Heydari, Mohammadali Tavakoli, Naomie Salim

Abstract:

In recent years, we have witnessed that online reviews are the most important source of customers’ opinion. They are progressively more used by individuals and organisations to make purchase and business decisions. Unfortunately, for the reason of profit or fame, frauds produce deceptive reviews to hoodwink potential customers. Their activities mislead not only potential customers to make appropriate purchasing decisions and organisations to reshape their business, but also opinion mining techniques by preventing them from reaching accurate results. Spam reviews could be divided into two main groups, i.e. multiple and singleton spam reviews. Detecting a singleton spam review that is the only review written by a user ID is extremely challenging due to lack of clue for detection purposes. Singleton spam reviews are very harmful and various features and proofs used in multiple spam reviews detection are not applicable in this case. Current research aims to propose a novel supervised technique to detect singleton spam reviews. To achieve this, various features are proposed in this study and are to be combined with the most appropriate features extracted from literature and employed in a classifier. In order to compare the performance of different classifiers, SVM and naive Bayes classification algorithms were used for model building. The results revealed that SVM was more accurate than naive Bayes and our proposed technique is capable to detect singleton spam reviews effectively.

Keywords: classification algorithms, Naïve Bayes, opinion review spam detection, singleton review spam detection, support vector machine

Procedia PDF Downloads 277

Authors: Aleksandra Dragojlov

Abstract:

Since the election of Aleksandar Vučić and the Progressives, Serbia has witnessed a slow decline in media freedom, which has been worse than in the 1990s. Although the government adopted a package of three laws in August 2014 to bring the media landscape up to European standards, the implementation of the laws has been limited and marginal, with the progressives engaging in fake compliance. The adoption of the new media strategy for 2020-2025 in 2020 has not led to genuine domestic reform and compliance with EU conditionality. In fact, the EU Commission and journalists’ associations in Serbia have criticised the decline in Serbia’s media freedom citing continued attacks on journalists and indirect political and economic control through advertising and project co-financing, which continue to be features of the Serbian media landscape. In the absence of clear and credible EU conditionality, the decline of media freedom is in the eye of the beholder, where the gap between public engagements with Serbian politicians and the critical stance of progress reports regarding the degradation of the media have enabled Serbian elites to exploit this ambiguity to continue their strategy of fake compliance vis-a-vis rule of law. This study used a mixed methods approach combining both primary and secondary sources with those semi-structured interviews via Zoom, email, and in person with EU and Serbian officials and journalists. Our findings add to the studies where the lack of clear and credible conditionality has allowed Serbia politicians to exploit them in a manner that would suit their own interests, finding new means to retain their control over the media. We argued and concluded that it is this discrepancy between public engagements with Serbia and the progress reports in the area of freedom of expression that has not led to genuine domestic media reforms in Serbia and instead allowed Serbian elites to engage in a strategy of fake and even non-compliance towards media freedom conditionality.

Keywords: media freedom, EU conditionality, Serbia, fake compliance, EU integration, Chapter 23, justice and fundamental rights

Procedia PDF Downloads 56

Authors: Jimmylen Tonio, Ali Anudin, Rochelle Irene G. Lucas

Abstract:

Alongside the progress of electronic-business websites, consumers have become more comfortable with online shopping. It has become customary for consumers that prior to purchasing a product or availing services, they consult online reviews info as bases in evaluating and deciding whether or not they should push thru with their procurement of the product or service. Subsequently, after purchasing, consumers tend to post their own comments of the product in the same e-business websites. Because of this, product reviews (PRS) have become an indispensable feature in online businesses equally beneficial for both business owners and consumers. This study explored the linguistic features and motivations of online product reviews on selected Philippine online shops, LAZADA and SHOPEE. Specifically, it looked into the lexical features of the PRs, the factors that motivated consumers to write the product reviews, and the difference of lexical preferences between male and female when they write the reviews. The findings revealed the following: 1. Formality of words in online product reviews primarily involves non-standard spelling, followed by abbreviated word forms, colloquial contractions and use of coined/novel words; 2. Paralinguistic features in online product reviews are dominated by the use of emoticons, capital letters and punctuations followed by the use of pictures/photos and lastly, by paralinguistic expressions; 3. The factors that motivate consumers to write product reviews varied. Online product reviewers are predominantly driven by venting negative feelings motivation, followed by helping the company, helping other consumers, positive self-enhancement, advice seeking and lastly, by social benefits; and 4. Gender affects the word frequencies of product online reviews, while negation words, personal pronouns, the formality of words, and paralinguistic features utilized by both male and female online product reviewers are not different.

Keywords: lexical choices, motivation, online shop, product reviews

Procedia PDF Downloads 107

Authors: Nidal F. Shilbayeh, Sameh T. Khuffash, Mohammad H. Allymoun, Reem Al-Saidi

Abstract:

There is a real threat on the VIPs personal pages on the Social Network Sites (SNS). The real threats to these pages is violation of privacy and theft of identity through creating fake pages that exploit their names and pictures to attract the victims and spread of lies. In this paper, we propose a new secure architecture that improves the trusting and finds an effective solution to reduce fake pages and possibility of recognizing VIP pages on SNS. The proposed architecture works as a third party that is added to Facebook to provide the trust service to personal pages for VIPs. Through this mechanism, it works to ensure the real identity of the applicant through the electronic authentication of personal information by storing this information within content of their website. As a result, the significance of the proposed architecture is that it secures and provides trust to the VIPs personal pages. Furthermore, it can help to discover fake page, protect the privacy, reduce crimes of personality-theft, and increase the sense of trust and satisfaction by friends and admirers in interacting with SNS.

Keywords: social network sites, online social network, privacy, trust, security and authentication

Procedia PDF Downloads 352