Ensemble Deep Learning for Multilabel Binary Classification of User-Generated Content

Haralabopoulos, Giannis; Anagnostopoulos, Ioannis; McAuley, Derek

doi:10.3390/a13040083

Cited by 51 publications

(19 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The embedding matrix is defined as the weights of an embedding layer. Then a Long-Term Short Memory (LSTM) [49] Table 9 represents more information about the quality of the classification.…”

Section: The First Strategy: Word2vec + Lstmmentioning

confidence: 99%

AI-Crime Hunter: An AI Mixture of Experts for Crime Discovery on Twitter

Shoeibi¹,

Hernández²,

Chamoso³

et al. 2021

Preprint

View full text Add to dashboard Cite

Maintaining a healthy cyber society is a big challenge due to the users’ freedom of expression and behaving. It can be solved by monitoring and analyzing the users’ behavior and taking proper actions towards them. This research aims to present a platform that monitors the public content on Twitter by extracting tweet data. After maintaining the data, the users’ interactions are analyzed using Graph Analysis methods. Then the users’ behavioral patterns are analyzed by applying Metadata Analysis, in which the timeline of each profile is obtained; also, the time-series behavioral features of users are investigated. Then in the Abnormal Behavior Detection Filtering component, the interesting profiles are selected for further examinations. Finally, in the Contextual Analysis component, the contents will be analyzed using natural language processing techniques; A binary text classification model (SVM + TF-IDF with 88.89% accuracy) for detecting if the tweet is related to crime or not. Then, a sentiment analysis method is applied to the crime-related tweets to perform aspect-based sentiment analysis (DistilBERT + FFNN with 80% accuracy); because sharing positive opinions about a crime-related topic can threaten society. This platform aims to provide the end-user (Police) suggestions to control hate speech or terrorist propaganda.

show abstract

Section: The First Strategy: Word2vec + Lstmmentioning

confidence: 99%

AI-Crime Hunter: An AI Mixture of Experts for Crime Discovery on Twitter

Shoeibi¹,

Hernández²,

Chamoso³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Classifying user interests is one of the most important steps in personalized advertising as it provides information about users’ interests that could be used by marketers or advertisers. There have been various studies to classify users’ interests [ 25 , 26 , 27 , 28 , 29 ]. A study on SNS suggests a classification method to classify users’ active communication through comments into a grading system using Word2vec and support vector machine (SVM) classifier [ 25 ].…”

Section: Related Workmentioning

confidence: 99%

“…A study on SNS suggests a classification method to classify users’ active communication through comments into a grading system using Word2vec and support vector machine (SVM) classifier [ 25 ]. The weighting ensemble model was proposed to classify the user’s emotions into multi-label binaries by analyzing the content created by the user, and this model performs the classification result without hyperparameter adjustment or overfitting [ 26 ]. Consumers buy products online, and there are many user comments regarding their decision of whether or not to make a purchase.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks

Hong

Choi

Lim

et al. 2020

Sensors

View full text Add to dashboard Cite

The classification and recommendation system for identifying social networking site (SNS) users’ interests plays a critical role in various industries, particularly advertising. Personalized advertisements help brands stand out from the clutter of online advertisements while enhancing relevance to consumers to generate favorable responses. Although most user interest classification studies have focused on textual data, the combined analysis of images and texts on user-generated posts can more precisely predict a consumer’s interests. Therefore, this research classifies SNS users’ interests by utilizing both texts and images. Consumers’ interests were defined using the Curlie directory, and various convolutional neural network (CNN)-based models and recurrent neural network (RNN)-based models were tested for our user interest classification system. In our hybrid neural network (NN) model, CNN-based classification models were used to classify images from users’ SNS postings while RNN-based classification models were used to classify textual data. The results of our extensive experiments show that the classification of users’ interests performed best when using texts and images together, at 96.55%, versus texts only, 41.38%, or images only, 93.1%. Our proposed system provides insights into personalized SNS advertising research and informs marketers on making (1) interest-based recommendations, (2) ranked-order recommendations, and (3) real-time recommendations.

show abstract

“…Text collections are labeled and analysed to create emotion detection and prediction algorithms [14]. Labelling can happen at paragraph, sentence, or term group level.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Aware Crowd Labelling for Machine Learning Tasks

Haralabopoulos¹,

Anagnostopoulos²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The extensive use of online social media has highlighted the importance of privacy in the digital space. As more scientists analyse the data created in these platforms, privacy concerns have extended to data usage within the academia. Although text analysis is a well documented topic in academic literature with a multitude of applications, ensuring privacy of user-generated content has been overlooked. Most sentiment analysis methods require emotion labels, which can be obtained through crowdsourcing, where non-expert individuals contribute to scientific tasks. The text itself has to be exposed to third parties in order to be labelled. In an effort to reduce the exposure of online users' information, we propose a privacy preserving text labelling method for varying applications, based in crowdsourcing. We transform text with different levels of privacy, and analyse the effectiveness of the transformation with regards to label correlation and consistency. Our results suggest that privacy can be implemented in labelling, retaining the annotational diversity and subjectivity of traditional labelling.

show abstract

Ensemble Deep Learning for Multilabel Binary Classification of User-Generated Content

Cited by 51 publications

References 52 publications

AI-Crime Hunter: An AI Mixture of Experts for Crime Discovery on Twitter

AI-Crime Hunter: An AI Mixture of Experts for Crime Discovery on Twitter

Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks

Privacy-Aware Crowd Labelling for Machine Learning Tasks

Contact Info

Product

Resources

About