Multi-label disaster text classification via supervised contrastive learning for social media data

Xie, Shaorong; Hou, Chunning; Yu, Hang; Zhang, Zhenyu; Luo, Xiangfeng; Zhu, Nengjun

doi:10.1016/j.compeleceng.2022.108401

Cited by 19 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bai et al (2022) took the sample feature as an anchor and the corresponding positive and negative labels as positive and negative samples, respectively, for supervised contrastive learning. Xie et al (2022) proposed a multi‐label classification framework based on supervised contrastive learning for data processing and model training.…”

Section: Related Workmentioning

confidence: 99%

A multi‐label social short text classification method based on contrastive learning and improved ml‐KNN

Tian,

Wang,

Wang

et al. 2024

Expert Systems

View full text Add to dashboard Cite

Short texts on social platforms often have the problems of diverse categories and semantic sparsity, making it challenging to identify the diverse intentions of users. To address this issue, this article proposes a multi‐label social short text classification method (IML‐CL) based on contrastive learning and improved ml‐KNN. First, a contrastive learning approach is employed to train a multi‐label text classification model. This approach improves semantic sparsity by leveraging the knowledge from the existing samples to enrich the feature representation of short texts. Simultaneously, an improved ml‐KNN algorithm is developed to enhance the accuracy of label prediction. This algorithm utilizes a two‐layer nearest neighbor rule and introduces a penalty function and weight optimization. Next, the model generates the feature representation for the test sample and predicts its label. Additionally, the improved ml‐KNN algorithm retrieves neighbors of the test sample and uses their label information for prediction. Finally, the two predictions are combined to obtain the final prediction, which accurately identifies the user's intention. The experimental results demonstrate that, on the dataset constructed in this article, the IML‐CL method effectively boosts the performance of the baseline model.

show abstract

Section: Related Workmentioning

confidence: 99%

A multi‐label social short text classification method based on contrastive learning and improved ml‐KNN

Tian,

Wang,

Wang

et al. 2024

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Similarly, in paper [29] developed a model for event detection during a disaster situation by Twitter using ML algorithms, such as RF, DT, and perceptron. Finally, in this work [30] a model for Twitter text analysis for disaster resource management was performed, where they incorporated a hybrid model with ML and CNN algorithms, resulting in reasonable accuracy and proving to be useful during these natural crises.…”

Section: Related Workmentioning

confidence: 99%

Classification of Tweets Related to Natural Disasters Using Machine Learning Algorithms

Iparraguirre-Villanueva,

Melgarejo-Graciano,

Castro-Leon

et al. 2023

Int. J. Interact. Mob. Technol.

View full text Add to dashboard Cite

Identifying and classifying text extracted from social networks, following the traditional method, is very complex. In recent years, computer science has advanced exponentially, helping significantly to identify and classify text extracted from social networks, specifically Twitter. This work aims to identify, classify and analyze tweets related to real natural disasters through tweets with the hashtag #NaturalDisasters, using Machine learning (ML) algorithms, such as Bernoulli Naive Bayes (BNB), Multinomial Naive Bayes (MNB), Logistic Regression (LR), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF). First, tweets related to natural disasters were identified, creating a dataset of 122k geolocated tweets for training. Secondly, the data-cleaning process was carried out by applying stemming and lemmatization techniques. Third, exploratory data analysis (EDA) was performed to gain an initial understanding of the data. Fourth, the training and testing process of the BNB, MNB, L, KNN, DT, and RF models was initiated, using tools and libraries for this type of task. The results of the trained models demonstrated optimal performance: BNB, MNB, and LR models achieved a performance rate of 87% accuracy; and KNN, DT, and RF models achieved performances of 82%, 75%, and 86%, respectively. However, the BNB, MNB, and LR models performed better with respect to performance on their respective metrics, such as processing time, test accuracy, precision, and F1 score. Demonstrating, for this context and with the trained dataset that they are the best in terms of text classifiers.

show abstract

“…In [19], a hybrid text multi-label classification method is constructed by combining a deep learning algorithm and a back-propagation neural network. In order to extend the size of the training data, a multi-label text classification based on a contrastive learning method is tested in [20] to classify disaster data extracted from social streams. The critical point of the multi-label text classification methods is the computational slowness in the semantic extraction and neural network construction processes.…”

Section: Related Workmentioning

confidence: 99%

A Fuzzy-Based Emotion Detection Method to Classify the Relevance of Pleasant/Unpleasant Emotions Posted by Users in Reviews of Service Facilities

2023

View full text Add to dashboard Cite

Many sentiment analysis methods have been proposed recently to evaluate, through the Web, the perceptions of users and their satisfaction with the use of products and services; these approaches have been applied in various fields in which it is necessary to evaluate, for example, the degree of appreciation of a product or a service or political orientations or emotional states following an event or the occurrence of a phenomenon. On the other hand, these methods are based on natural language processing models needed to capture information hidden in comments, which generally require a high computational cost which can affect their performance; for this reason, review-collecting providers prefer to synthetically evaluate user satisfaction by considering a score on a numerical scale entered by users. To overcome this criticality, we propose an emotion detection method based on a light fuzzy-based document classification model to capture the relevance of pleasant and unpleasant emotions expressed by users in their reviews of service facilities. This method is implemented in a geo-computational framework and tested to evaluate the satisfaction of customers of theater venues located in the municipality of Naples (Italy). A fuzzy-based approach is used to classify user satisfaction according to the relevance of the emotional categories of pleasant and unpleasant. We show that our emotion detection method refines service feature pleasure assessments expressed on scales by users in their reviews.

show abstract

Multi-label disaster text classification via supervised contrastive learning for social media data

Cited by 19 publications

References 12 publications

A multi‐label social short text classification method based on contrastive learning and improved ml‐KNN

A multi‐label social short text classification method based on contrastive learning and improved ml‐KNN

Classification of Tweets Related to Natural Disasters Using Machine Learning Algorithms

A Fuzzy-Based Emotion Detection Method to Classify the Relevance of Pleasant/Unpleasant Emotions Posted by Users in Reviews of Service Facilities

Contact Info

Product

Resources

About