Fuzzy rough nearest neighbour methods for detecting emotions, hate speech and irony

Kaminska, Olha; Cornelis, Chris; Hoste, Véronique

doi:10.1016/j.ins.2023.01.054

Cited by 12 publications

(4 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The datasets for these experiments originate from different SemEval competitions (https://semeval.github.io/, accessed on 14 January 2023). While the majority of the best-performing solutions submitted to these competitions were based on neural networks or transformers, our solutions achieved comparable results and were consistently ranked among the TOP-5 results, as demonstrated in [5]. At the same time, we were able to provide interpretability of our solution (as also demonstrated in Section 6), which is an important advantage when dealing with a subjective topic such as emotions.…”

Section: Introductionsupporting

confidence: 59%

“…Fuzzy rough set approaches have been successfully applied in different machine learning tasks [24], for example, in rule-based classifiers [25], imbalanced data learning [26], fuzzy rough neural networks [27], etc. In our own previous work, we explored the usage of fuzzy-rough-based models for emotion classification tasks in [3][4][5], where we not only showed that our results were competitive to the state-of-the-art, but also that fuzzyrough nearest neighbour classification methods allow for a more transparent detection of particular patterns in the prediction process.…”

Section: Description Of Our Previous Workmentioning

confidence: 91%

“…We also used more preprocessing methods and model confidence scores, which led us to third place in the same SemEval competition leaderboard. Later, we applied this approach to more datasets, for example, sarcasm in [4] and hate speech and irony in [5]. In the current paper, we investigate with which accuracy the different subtasks of ABSA can be tackled with fuzzy-rough nearest neighbour-based classification methods.…”

Section: Description Of Our Previous Workmentioning

confidence: 99%

“…Previously, such techniques were already used for various other machine learning tasks, including in sentiment analysis and emotion detection. In particular, in [3][4][5], we investigated the application of fuzzy-rough methods for emotion categorisation, irony and hate speech detection. The datasets for these experiments originate from different SemEval competitions (https://semeval.github.io/, accessed on 14 January 2023).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fuzzy Rough Nearest Neighbour Methods for Aspect-Based Sentiment Analysis

2023

Self Cite

View full text Add to dashboard Cite

Fine-grained sentiment analysis, known as Aspect-Based Sentiment Analysis (ABSA), establishes the polarity of a section of text concerning a particular aspect. Aspect, sentiment, and emotion categorisation are the three steps that make up the configuration of ABSA, which we looked into for the dataset of English reviews. In this work, due to the fuzzy nature of textual data, we investigated machine learning methods based on fuzzy rough sets, which we believe are more interpretable than complex state-of-the-art models. The novelty of this paper is the use of a pipeline that incorporates all three mentioned steps and applies Fuzzy-Rough Nearest Neighbour classification techniques with their extension based on ordered weighted average operators (FRNN-OWA), combined with text embeddings based on transformers. After some improvements in the pipeline’s stages, such as using two separate models for emotion detection, we obtain the correct results for the majority of test instances (up to 81.4%) for all three classification tasks. We consider three different options for the pipeline. In two of them, all three classification tasks are performed consecutively, reducing data at each step to retain only correct predictions, while the third option performs each step independently. This solution allows us to examine the prediction results after each step and spot certain patterns. We used it for an error analysis that enables us, for each test instance, to identify the neighbouring training samples and demonstrate that our methods can extract useful patterns from the data. Finally, we compare our results with another paper that performed the same ABSA classification for the Dutch version of the dataset and conclude that our results are in line with theirs or even slightly better.

show abstract

Section: Introductionsupporting

confidence: 59%

Section: Description Of Our Previous Workmentioning

confidence: 91%

Section: Description Of Our Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fuzzy Rough Nearest Neighbour Methods for Aspect-Based Sentiment Analysis

2023

Self Cite

View full text Add to dashboard Cite

show abstract

Classifying Token Frequencies Using Angular Minkowski p-Distance

Lenz,

Cornelis

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A comprehensive review on automatic hate speech detection in the age of the transformer

Ramos,

Batista,

Ribeiro

et al. 2024

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

The rapid proliferation of hate speech on social media poses significant challenges to maintaining a safe and inclusive digital environment. This paper presents a comprehensive review of automatic hate speech detection methods, with a particular focus on the evolution of approaches from traditional machine learning and deep learning models to the more advanced Transformer-based architectures. We systematically analyze over 100 studies, comparing the effectiveness, computational requirements, and applicability of various techniques, including Support Vector Machines, Long Short-Term Memory networks, Convolutional Neural Networks, and Transformer models like BERT and its multilingual variants. The review also explores the datasets, languages, and sources used for hate speech detection, noting the predominance of English-focused research while highlighting emerging efforts in low-resource languages and cross-lingual detection using multilingual Transformers. Additionally, we discuss the role of generative and multi-task learning models as promising avenues for future development. While Transformer-based models consistently achieve state-of-the-art performance, this review underscores the trade-offs between performance and computational cost, emphasizing the need for context-specific solutions. Key challenges such as algorithmic bias, data scarcity, and the need for more standardized benchmarks are also identified. This review provides crucial insights for advancing the field of hate speech detection and shaping future research directions.

show abstract

Fuzzy rough nearest neighbour methods for detecting emotions, hate speech and irony

Cited by 12 publications

References 47 publications

Fuzzy Rough Nearest Neighbour Methods for Aspect-Based Sentiment Analysis

Fuzzy Rough Nearest Neighbour Methods for Aspect-Based Sentiment Analysis

Classifying Token Frequencies Using Angular Minkowski p-Distance

A comprehensive review on automatic hate speech detection in the age of the transformer

Contact Info

Product

Resources

About