219 Hits in 3.1 sec

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

Giannis Haralabopoulos, Ioannis Anagnostopoulos, Derek McAuley
2020 Algorithms  
Multilabel classifiers can categorize human-generated content in multiple emotional classes.  ...  Our results suggest that ensemble learning improves classification results by 1.5 % to 5.4 % .  ...  User-generated content provides a unique combination of complexity and challenge for automated sentiment classification.  ... 
doi:10.3390/a13040083 fatcat:vdcqiyqjvvevjlgrfqbigbtbze

Special Issue on Ensemble Learning and Applications

Panagiotis Pintelas, Ioannis E. Livieris
2020 Algorithms  
In the literature, ensemble learning algorithms constitute a dominant and state-of-the-art approach for obtaining maximum performance, thus they have been applied in a variety of real-world problems ranging  ...  During the last decades, in the area of machine learning and data mining, the development of ensemble methods has gained a significant attention from the scientific community.  ...  Conflicts of Interest: The guest editors declare no conflict of interest. Algorithms 2020, 13, 140  ... 
doi:10.3390/a13060140 doaj:d88cf17ddc964a1ba88956be2615d4b1 fatcat:ejpubra5mffe7l4gsfiuirurlm

Automated Social Text Annotation With Joint Multilabel Attention Networks

Hang Dong, Wei Wang, Kaizhu Huang, Frans Coenen
2020 IEEE Transactions on Neural Networks and Learning Systems  
We propose a novel deep learning-based method for this problem and design an attention-based neural network with semantic-based regularization, which can mimic users' reading and annotation behavior to  ...  It can be formulated as a multilabel classification problem.  ...  ACKNOWLEDGMENT Part of this work has made use of the resources provided by the Edinburgh Compute and Data Facility (ECDF) (  ... 
doi:10.1109/tnnls.2020.3002798 pmid:32584774 fatcat:b6vkhubjtbcrpg3fk2w7z6rsae

A Comprehensive and Didactic Review on Multilabel Learning Software Tools

Francisco Charte
2020 IEEE Access  
Thus, a multilabel classifier generates a set of outputs instead of only one as a standard classifier does. However, software tools for multilabel learning tend to be scarce.  ...  SPECIFICS OF MULTILABEL LEARNING VS. STANDARD LEARNING  ...  The capability to use Keras in order to build deep learning-based multilabel models is also included.  ... 
doi:10.1109/access.2020.2979787 fatcat:erkp3vf6ufaaxkm554xk3vsr3i

Analysis of multiobjective algorithms for the classification of multi-label video datasets

Gizem Nur Karagoz, Adnan Yazici, Tansel Dokeroglu, Ahmet Cosar
2020 IEEE Access  
Tagging this rich data content with simple binary labels may not be possible in many cases. For this reason, multi-label classification is an important field of data classification.  ...  Three multi-objective feature selection methods for binary classification problems with machine learning are proposed in a recent study [19] .  ... 
doi:10.1109/access.2020.3022317 fatcat:tfpr76ndjvbkdbyj4h7etdhyli

Combining Context-aware Embeddings and an Attentional Deep Learning Model for Arabic Affect Analysis on Twitter

Hanane Elfaik, El Habib Nfaoui
2021 IEEE Access  
In this paper, we address the problem of Arabic affect detection (multilabel emotion classification) by combining the transformer-based model for Arabic language understanding AraBERT and an attention-based  ...  LSTM-BiLSTM deep model.  ...  TABLE X ARABIC X EMOTION CLASSIFICATION USING TOP PERFORMERS OF THE DEEP LEARNING MODELS.The third set of experiments is dedicated to multilabel Arabic emotion classification using the top performers of  ... 
doi:10.1109/access.2021.3102087 fatcat:4y4ah7mxnzf7dfuducohavjboy

Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Training [article]

Vikram Gupta
2021 arXiv   pre-print
However, the efficacy of VAT for multilingual and multilabel text classification has not been explored before.  ...  supervised learning with same amount of labelled data (10% of training data).  ...  Binary relevance approach (Godbole and Sarawagi, 2004) is another way to break multilabel problem into multiple binary classification problems.  ... 
arXiv:2111.06181v1 fatcat:v4ws64kzajbedd4p2hrc2vucre

Real Estate Recommendation Approach for Solving the Item Cold-Start Problem

Jirut Polohakul, Ekapol Chuangsuwanich, Atiwong Suchato, Proadpran Punyabukkana
2021 IEEE Access  
This enables us to generate an adequate number of training sequences for deep learning. C.  ...  The prediction of each class is a binary classification problem. Furthermore, it is a multilabel classification problem when grouping such predictions as a feature prediction.  ... 
doi:10.1109/access.2021.3077564 fatcat:adcliphj3fdb3ookmhc5hznnhe

Facial Expression Recognition: A Review of Trends and Techniques

Olufisayo Ekundayo, Serestina Viriri
2021 IEEE Access  
Furthermore, popularly employed FER models are thoroughly and carefully discussed in handcrafted, conventional machine learning and deep learning models.  ...  We proceed to provide a comprehensive FER review in three different machine learning problem definitions: Single Label Learning (SLL)-which presents FER as a multiclass problem, Multilabel Learning (MLL  ...  The work of [30] is also a multilabel approach to FER, Li and Deng [30] introduced a multilabel deep learning model termed Deep Bi-Manifold CNN (DBM-CMM).  ... 
doi:10.1109/access.2021.3113464 fatcat:hapy6t6ohneupiwh7meakzk3ma

Latent Personality Traits Assessment From Social Network Activity Using Contextual Language Embedding

Pavan Kumar K. N., Marina L. Gavrilova
2021 IEEE Transactions on Computational Social Systems  
Users reveal aspects of their personality via the content they share with their social media followers and through the patterns in their interactions on online networking platforms.  ...  The developed system outperforms the state-of-the-art research by reliably estimating the user's latent personality traits while using 50 or fewer tweets per user.  ...  For each user, the content of their tweets can be considered as the linguistic style they use on Twitter.  ... 
doi:10.1109/tcss.2021.3108810 fatcat:ni2fea2hkndjpjxkl6f5tl7g4m

Automatic image annotation method based on a convolutional neural network with threshold optimization

Jianfang Cao, Aidi Zhao, Zibang Zhang
2020 PLoS ONE  
When the prediction probability for this class of labels is greater than or equal to the corresponding optimal threshold, this class of labels is used as the annotation result for the image.  ...  in the use of a ranking function for label annotation along with prediction probability.  ...  of ensemble learning to improve the annotation accuracy.  ... 
doi:10.1371/journal.pone.0238956 pmid:32966319 pmcid:PMC7511011 fatcat:tl47iyp7hbhudnb4x5t7m56yni

Machine learning methods for toxic comment classification: a systematic review

Darko Andročec
2020 Acta Universitatis Sapientiae: Informatica  
We finish our work with comprehensive list of gaps in current research and suggestions for future research themes related to online toxic comment classification problem.  ...  In this work, we performed a systematic review of the state-of-the-art in toxic comment classification using machine learning methods. We extracted data from 31 selected primary relevant studies.  ...  dependencies in the sentences [29] S17 Empirical Analysis of Multi-Task Learning for Reducing Model Bias in Toxic Comment Detection [31] S18 Ensemble Deep Learning for Multilabel Binary Classification  ... 
doi:10.2478/ausi-2020-0012 fatcat:pkza7bs7mbgfffvnedyednzs34

Classification-based Deep Neural Network Architecture for Collaborative Filtering Recommender Systems

Jesús Bobadilla, Fernando Ortega, Abraham Gutiérrez, Santiago Alonso
2020 International Journal of Interactive Multimedia and Artificial Intelligence  
The learning process is based on the binary relevant/non-relevant vote and the binary voted/ non-voted item information.  ...  This paper proposes a scalable and original classification-based deep neural architecture.  ...  The MF machine learning algorithm needs to learn a set of F factors for each user (U) and for each item (I) in the dataset.  ... 
doi:10.9781/ijimai.2020.02.006 fatcat:ywuaoz3ne5eyxbwxjahcnctja4

Music Genre Classification using Deep Learning

Sheeba Fathima
2021 International Journal for Research in Applied Science and Engineering Technology  
Machine learning techniques were used to classify music genres in this research. Deep neural networks (DNN) have recently been demonstrated to be effective in a variety of classification tasks.  ...  In this paper, we propose two methods for boosting music genre classification with convolutional neural networks: 1) using a process inspired by residual learning to combine peak- and average pooling to  ...  ., (2002) .They presented their research on audio content segmentation and classification in content review for audio segmentation and classification.  ... 
doi:10.22214/ijraset.2021.36087 fatcat:2tkneqaehrb6nd6atng3ifgziq

The Emerging Trends of Multi-Label Learning [article]

Weiwei Liu, Xiaobo Shen, Haobo Wang, Ivor W. Tsang
2020 arXiv   pre-print
Besides these, there are tremendous efforts on how to harvest the strong learning capability of deep learning to better capture the label dependencies in multi-label learning, which is the key for deep  ...  Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data.  ...  All these works study the generalization error and consistency of learning approaches which address multi-label learning by decomposing into a set of binary classification problems.  ... 
arXiv:2011.11197v2 fatcat:hu6w4vgnwbcqrinrdfytmmjbjm
« Previous Showing results 1 — 15 out of 219 results