Conspiracy or Not? A Deep Learning Approach to Spot It on Twitter

Galende, Borja Arroyo; Hernández-Peñaloza, Gustavo; Uribe, Silvia; Álvarez, Federico

doi:10.1109/access.2022.3165226

Cited by 7 publications

(7 citation statements)

References 26 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…compared accuracy with the other models which are using the same datasets. Further, to support the effectiveness of the suggested algorithm, we compared the experimental findings with the Fake News diagnosis parameters results in terms of accuracy, precision, recall, and F1-score [22]. As we can see in fig.…”

Section: ) Isotmentioning

confidence: 87%

Fake News Detection System Using Featured-Based Optimized MSVM Classification

et al. 2022

View full text Add to dashboard Cite

Fake News creates erroneous suspense information that can be identified. This spreads dishonesty about a country's status or overstates the expense of special functions for a government, destroying democracy in certain countries, such as in the Arab Spring. Associations such as the ''House of Commons and the Crosscheck project'' address concerns such as publisher responsibility. However, since they rely entirely on manual detection by humans, their coverage is minimal. This is neither sustainable nor possible in a world where billions of items are withdrawn or posted every second. The paper produces a deep study on past research work on fake news detection on the selected data-sets and proposes an algorithm with Multi-layered Principal Component Analysis for feature selection followed by firefly-optimized algorithm. Multi-Support Vector Machines(MSVM) are finally used to classify the news. We used ten different data-sets for testing the proposed algorithm. As the number of features in the data-sets are more, feature extration and selection methods help to improve the accuracy in respective data-sets. Only the datasets having less number of features gave a lower performance on our feature extraction algorithms. INDEX TERMSFake news, rirefly, long short-term memory (LSTM), multi support vector machine (MSVM).

show abstract

Section: ) Isotmentioning

confidence: 87%

Fake News Detection System Using Featured-Based Optimized MSVM Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Existing literature often focuses on misinformation (Lin et al 2019;Kumar et al 2020) or specific conspiracy theories related to COVID-19, alien visitation, anti-vaccination, white genocide, climate change, or Jeffery Epstein (Moffitt, King, and Carley 2021;Marcellino et al 2021;Phillips, Ng, and Carley 2022). Most works focus mainly on Tweets as the unit of the study (Moffitt, King, and Carley 2021;Galende et al 2022;Phillips, Ng, and Carley 2022;Mahl, Zeng, and Schäfer 2021). For example, Galende et al (2022) study Tweets explicitly containing the word "conspiracy."…”

Section: Conspiracy Detectionmentioning

confidence: 99%

“…Most works focus mainly on Tweets as the unit of the study (Moffitt, King, and Carley 2021;Galende et al 2022;Phillips, Ng, and Carley 2022;Mahl, Zeng, and Schäfer 2021). For example, Galende et al (2022) study Tweets explicitly containing the word "conspiracy." Phillips, Ng, and Carley (2022) Conspiracy Taxonomy Mahl, Zeng, and Schäfer (2021) used network analysis of co-occurring hashtags in Tweets to assign hashtags into topic groups qualitatively based on their thematic relationship.…”

Section: Conspiracy Detectionmentioning

confidence: 99%

See 1 more Smart Citation

YouNICon: YouTube’s CommuNIty of Conspiracy Videos

Liaw

Fan

Benevenuto

et al. 2023

ICWSM

View full text Add to dashboard Cite

Conspiracy theories are widely propagated on social media. Among various social media services, YouTube is one of the most influential sources of news and entertainment. This paper seeks to develop a dataset, YOUNICON, to enable researchers to perform conspiracy theory detection as well as classification of videos with conspiracy theories into different topics. YOUNICON is a dataset with a large collection of videos from suspicious channels that were identified to contain conspiracy theories in a previous study. Overall, YOUNICON will enable researchers to study trends in conspiracy theories and understand how individuals can interact with the conspiracy theory producing community or channel. Our data is available at: https://doi.org/10.5281/zenodo.7466262.

show abstract

“…The trained model is then used to identify the class label of new unseen test data. In unsupervised learning, the model automatically finds patterns and relationships in the dataset by creating clusters in it [2]. Reinforcement learning aims to develop a system or an agent that learns from the rewards and punishments received from the environment In document-level sentiment classification, lexical, syntactic, and semantic features in a document are first extracted.…”

Section: Introductionmentioning

confidence: 99%

Survey of Deep Learning Approaches for Twitter Text Classification

Kadu¹,

Deshpande²,

Pawar³

2022

IJAERS

View full text Add to dashboard Cite

Sentiment analysis (also known as opinion mining or emotion AI) is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine. With the rise of deep language models, such as RoBERTa, also more difficult data domains can be analyzed, e.g., news texts where authors typically express their opinion/sentiment less explicitly. Sentiment analysis aims to extract opinion automatically from data and classify them as positive and negative. Twitter widely used social media tools, been seen as an important source of information for acquiring people’s attitudes, emotions, views, and feedbacks. Within this context, Twitter sentiment analysis techniques were developed to decide whether textual tweets express a positive or negative opinion. In contrast to lower classification performance of traditional algorithms, deep learning models, including Convolution Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM), have achieved a significant result in sentiment analysis. Keras is a Deep Learning (DL) framework that provides an embedding layer to produce the vector representation of words present in the document. The objective of this work is to analyze the performance of deep learning models namely Convolutional Neural Network (CNN), Simple Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM), bidirectional Long Short-Term Memory (Bi-LSTM), BERT and RoBERTa for classifying the twitter reviews. From the experiments conducted, it is found that RoBERTa model performs better than CNN and simple RNN for sentiment classification.

show abstract

Conspiracy or Not? A Deep Learning Approach to Spot It on Twitter

Cited by 7 publications

References 26 publications

Fake News Detection System Using Featured-Based Optimized MSVM Classification

Fake News Detection System Using Featured-Based Optimized MSVM Classification

YouNICon: YouTube’s CommuNIty of Conspiracy Videos

Survey of Deep Learning Approaches for Twitter Text Classification

Contact Info

Product

Resources

About