Deep Learning Approaches to Overcome Challenges in Forensics

2021 ◽  
pp. 81-92
Author(s):  
Kiruthigha M. ◽  
Senthil Velan S.
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Social Network ◽  
Social Networking ◽  
Learning Approaches ◽  
Network Forensics ◽  
Cyber Forensics ◽  
Speed Up ◽  
Online Sources ◽  
Gain Access

Cyber forensics deals with collecting, extracting, analysing, and finally reporting the evidence of a crime. Typically investigating a crime takes time. Involving deep learning methods in cyber forensics can speed up the investigation procedure. Deep learning incorporates areas like image classification, morphing, and behaviour analysis. Forensics happens where data is. People share their activities, pictures, videos, and locations visited on the readily available platform, social media. An abundance of information available on social networking platforms renders them a favourite of cybercriminals. Compromising a profile, a hacker can gain access, modify, and use its data for various activities. Unscrupulous activities on such platforms include stalking, bullying, defamation, circulation of illegal or pornographic material, etc. Social network forensics is more than the application of computer investigation and analysis techniques, such as collecting information from online sources. CNNs and autoencoders can learn and obtain features from an image.

scholarly journals La interactividad en medios sociales: un estudio de caso / Social Media Interactivity: a Case Study

2012 ◽  
Vol 1 (2) ◽  
Author(s):  
Joan Francesc Fondevila Gascón ◽  
Ana Beriain
Keyword(s):  
Social Media ◽  
Social Network ◽  
Empirical Study ◽  
Social Networking ◽  
Point Of View ◽  
Redes Sociales ◽  
Psychological Point ◽  
Medios Sociales ◽  
Estudio De Caso

ABSTRACTThe social networking phenomenon starts generating various investigations, but so far none has raised the relationships among users of a social network from the behavioral and psychological point of view. To this end, we have conducted an empirical study based on simulated profiles in Facebook, relevant social network due to the amount of available users and for its IPO. From imaginary profiles, we analyze the types of other Facebook users that are added, which can inspire ecommerce strategies related to digital newspapers.RESUMENEl fenómeno de las redes sociales comienza a generar investigaciones diversas, pero de momento ninguna ha planteado las relaciones entre los usuarios de una red social desde el punto de vista conductual y psicológico. A tal efecto, hemos llevado a cabo un estudio empírico a partir de una simulación de perfiles en Facebook, red social de referencia por la cantidad de usuarios disponibles y por su salida a bolsa. A partir de perfiles imaginarios, analizamos la tipología de otros usuarios de Facebook que se le agregan, lo que puede inspirar estrategias de comercio electrónico vinculadas a los periódicos digitales.

Role of Social Media in Tourism

2015 ◽  
pp. 142-162
Author(s):  
Vipin K. Nadda ◽  
Sumesh Singh Dadwal ◽  
Dirisa Mulindwa ◽  
Rubina Vieira
Keyword(s):  
Social Networks ◽  
Information Technology ◽  
Social Media ◽  
Social Network ◽  
Social Networking ◽  
Web Sites ◽  
User Generated Content ◽  
Major Shift ◽  
Tourism And Hospitality

Revolutionary development in field of communication and information technology have globally opened new avenue of marketing tourism and hospitality products. Major shift in web usage happened when Napster in 1999 released peer-to-peer share media and then with pioneer social networking websites named ‘Six Degrees'. This kind of interactive social web was named as ‘Web 2.0'. It would create openness, community and interaction. Web2. is also known as Social media base. Social media is incudes “all the different kinds of content that form social networks: posts on blogs or forums, photos, audio, videos, links, profiles on social networking web sites, status updates and more”. It allows people to create; upload post and share content easily and share globally. Social media allows the creation and exchange of user-generated content and experiences online. Thus, social media is any kind of information we share with our social network, using social networking web sites and services.

scholarly journals Detecting Traffic Information From Social Media Texts With Deep Learning Approaches

2019 ◽  
Vol 20 (8) ◽  
pp. 3049-3058 ◽  
Author(s):  
Yuanyuan Chen ◽  
Yisheng Lv ◽  
Xiao Wang ◽  
Lingxi Li ◽  
Fei-Yue Wang
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Traffic Information ◽  
Learning Approaches ◽  
Media Texts

CID: Categorical Influencer Detection on microtext-based social media

2020 ◽  
Vol 44 (5) ◽  
pp. 1027-1055
Author(s):  
Thanh-Tho Quan ◽  
Duc-Trung Mai ◽  
Thanh-Duy Tran
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Learning Approaches ◽  
Content Type ◽  
Modeling Process ◽  
Variational Autoencoder ◽  
Media Channels

PurposeThis paper proposes an approach to identify categorical influencers (i.e. influencers is the person who is active in the targeted categories) in social media channels. Categorical influencers are important for media marketing but to automatically detect them remains a challenge.Design/methodology/approachWe deployed the emerging deep learning approaches. Precisely, we used word embedding to encode semantic information of words occurring in the common microtext of social media and used variational autoencoder (VAE) to approximate the topic modeling process, through which the active categories of influencers are automatically detected. We developed a system known as Categorical Influencer Detection (CID) to realize those ideas.FindingsThe approach of using VAE to simulate the Latent Dirichlet Allocation (LDA) process can effectively handle the task of topic modeling on the vast dataset of microtext on social media channels.Research limitations/implicationsThis work has two major contributions. The first one is the detection of topics on microtexts using deep learning approach. The second is the identification of categorical influencers in social media.Practical implicationsThis work can help brands to do digital marketing on social media effectively by approaching appropriate influencers. A real case study is given to illustrate it.Originality/valueIn this paper, we discuss an approach to automatically identify the active categories of influencers by performing topic detection from the microtext related to the influencers in social media channels. To do so, we use deep learning to approximate the topic modeling process of the conventional approaches (such as LDA).

scholarly journals Unplugged

2018 ◽  
Author(s):  
Lea Powell
Keyword(s):  
Social Media ◽  
Social Network ◽  
Social Networking ◽  
Real Life ◽  
Positive Influence ◽  
Self Image ◽  
Unrealistic Expectations

This article serves as an explorative piece attempting to investigate social networking norms and their contribution towards increased levels of disengagement and disconnection. After recognizing superficial online trends of interaction within her own social network, the author discloses experiencing feelings of hopelessness. In attempt to explore these feelings and unmask the factors underlying these trends, elements of motivation, privacy, and an individual’s relationship with control are discussed. Themes of expectant accessibility and communication within the realm of technology are explored and compared to real life interactions and experiences, with emphasis on an observed dissonance occurring between them. Notions of social networking's contribution to unrealistic expectations of self-image and worth are addressed to caution the reader against over-embellishment and the risks associated with distorted representations of self. Concluding remarks credit the positive influence of social networking’s impact on society while warranting further investigation from the reader. Readers are encouraged to reflect on the topics in attempt to establish their own healthy, balanced relationship with technology and social media.

scholarly journals Comparative Analysis of Deep Learning Techniques to detect Online Public Shaming

2021 ◽  
Vol 40 ◽  
pp. 03030
Author(s):  
Mehdi Surani ◽  
Ramchandra Mangrulkar
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Freedom Of Speech ◽  
Learning Approaches ◽  
Learning Models ◽  
Media Usage ◽  
The Past ◽  
Learning Techniques ◽  
Social Media Platforms ◽  
Machine Learning Models

Over the past years the exponential growth of social media usage has given the power to every individual to share their opinions freely. This has led to numerous threats allowing users to exploit their freedom of speech, thus spreading hateful comments, using abusive language, carrying out personal attacks, and sometimes even to the extent of cyberbullying. However, determining abusive content is not a difficult task and many social media platforms have solutions available already but at the same time, many are searching for more efficient ways and solutions to overcome this issue. Traditional models explore machine learning models to identify negative content posted on social media. Shaming categories are explored, and content is put in place according to the label. Such categorization is easy to detect as the contextual language used is direct. However, the use of irony to mock or convey contempt is also a part of public shaming and must be considered while categorizing the shaming labels. In this research paper, various shaming types, namely toxic, severe toxic, obscene, threat, insult, identity hate, and sarcasm are predicted using deep learning approaches like CNN and LSTM. These models have been studied along with traditional models to determine which model gives the most accurate results.

scholarly journals Detect Extreme Sentiments on Social Networks using BERT

2021 ◽  
Author(s):  
Muhammad Luqman Jamil ◽  
Sebastião Pais ◽  
João Cordeiro ◽  
Gaël Dias
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Public Opinion ◽  
Social Network ◽  
Social Networking ◽  
Online Social Networking ◽  
Social Media Data ◽  
Preceding Work ◽  
Unsupervised Approach ◽  
Media Data

Abstract Online social networking platforms allow people to freely express their ideas, opinions, and emotions negatively or positively. Previous studies have examined user’s sentiments on these platforms to study their behaviour in different contexts and purposes. The mechanism of collecting public opinion information has attracted researchers to automatically classify the polarity of public opinions based on the use of concise language in messages, such as tweets, by analyzing social media data. In this paper, we extend the preceding work [1], by proposing an unsupervised approach to automatically detect extreme opinions/posts in social networks. We have evaluated our performance on five different social network and media datasets. In this work, we use the semi-supervised approach BERT to check the accuracy of our classified dataset. The latter task shows that, in these datasets, posts that were previously classified as negative or positive are, in fact, extremely negative or positive in many cases.

scholarly journals Public Trolling Detection on Twitter Using Machine Learning

2021 ◽  
Vol 9 (VII) ◽  
pp. 3097-3100
Author(s):  
Miss. Pooja Dilip Dhotre
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Social Network ◽  
Social Networking ◽  
Social Networking Sites ◽  
Machine Learning Algorithms ◽  
The People ◽  
The World ◽  
Added Benefit ◽  
Current Popularity

Social media websites are among the internet's most far-reaching digital sites. Billions of social network users exist Users' frequent interactions with social networking sites, like Twitter, have a widespread and sometimes unfortunate effect on day-to-day life. Social networking sites make it easy for large amounts of unwanted and unrelated information to spread around the world. Twitter is a popular micro blogging service where users connect with others with similar interests. Because of the current popularity of Twitter, it is vulnerable to public shaming. Recently, Twitter has emerged as a rich source of human-generated information, with the added benefit of connecting you with customers and enabling two-way communication. It is generally accepted that when someone posts a comment in an occurrence, it is likely to humiliate the victim. The fact that shaming users' follower counts increase faster than that of the people who don't use shame is interesting. Using machine learning algorithms, users will be able to identify disrespectful words, as well as the overall negativity of those words, which is displayed in a percentage.

Deep Learning Method for Prediction of DDoS Attacks on Social Media

2019 ◽  
Vol 11 (01n02) ◽  
pp. 1950002
Author(s):  
Rasim M. Alguliyev ◽  
Ramiz M. Aliguliyev ◽  
Fargana J. Abdullayeva
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Social Networking ◽  
Cyber Attacks ◽  
Test Accuracy ◽  
Learning Method ◽  
Ddos Attacks ◽  
Twitter Data ◽  
Social Events

Recently, data collected from social media enable to analyze social events and make predictions about real events, based on the analysis of sentiments and opinions of users. Most cyber-attacks are carried out by hackers on the basis of discussions on social media. This paper proposes the method that predicts DDoS attacks occurrence by finding relevant texts in social media. To perform high-precision classification of texts to positive and negative classes, the CNN model with 13 layers and improved LSTM method are used. In order to predict the occurrence of the DDoS attacks in the next day, the negative and positive sentiments in social networking texts are used. To evaluate the efficiency of the proposed method experiments were conducted on Twitter data. The proposed method achieved a recall, precision, [Formula: see text]-measure, training loss, training accuracy, testing loss, and test accuracy of 0.85, 0.89, 0.87, 0.09, 0.78, 0.13, and 0.77, respectively.

Sign in / Sign up

Export Citation Format

Share Document