Within textual emotion classification, the set of relevant labels depends on the domain and application scenario and might not be known at the time of model development. This conflicts with the classical paradigm of supervised learning in which the labels need to be predefined. A solution to obtain a model with a flexible set of labels is to use the paradigm of zero-shot learning as a natural language inference task, which in addition adds the advantage of not needing any labeled training data. This raises the question how to prompt a natural language inference model for zero-shot learning emotion classification. Options for prompt formulations include the emotion name anger alone or the statement "This text expresses anger". With this paper, we analyze how sensitive a natural language inference-based zero-shot-learning classifier is to such changes to the prompt under consideration of the corpus: How carefully does the prompt need to be selected? We perform experiments on an established set of emotion datasets presenting different language registers according to different sources (tweets, events, blogs) with three natural language inference models and show that indeed the choice of a particular prompt formulation needs to fit to the corpus. We show that this challenge can be tackled with combinations of multiple prompts. Such ensemble is more robust across corpora than individual prompts and shows nearly the same performance as the individual best prompt for a particular corpus.
Emotion Classification through EEG signals has achieved many advancements. However, the problems like lack of data and learning the important features and patterns have always been areas with scope for improvement both computationally and in prediction accuracy. This works analyses the baseline machine learning classifiers' performance on DEAP Dataset along with a tabular learning approach that provided state-of-the-art comparable results leveraging the performance boost due to its deep learning architecture without deploying heavy neural networks.
The classification of electroencephalography (EEG) signals is useful in a wide range of applications such as seizure detection/prediction, motor imagery classification, emotion classification and drug effects diagnosis, amongst others. With the large number of EEG channels acquired, it has become vital that efficient data-reduction methods are developed, with varying importance from one application to another. It is also important that online classification is achieved during EEG recording for many applications, to monitor changes as they happen. In this paper we introduce a method based on Mutual Information (MI), for channel selection. Obtained results show that whilst there is a penalty on classification accuracy scores, promising speed-up gains can be achieved using MI techniques. Using MI with signal epochs (3secs) containing signal transitions enhances these speed-up gains. This work is exploratory and we suggest further research to be carried out for validation and development. Benefits to improving classification speed include improving application in clinical or educational settings.
In this work, a kernel attention module is presented for the task of EEG-based emotion classification with neural networks. The proposed module utilizes a self-attention mechanism by performing a kernel trick, demanding significantly fewer trainable parameters and computations than standard attention modules. The design also provides a scalar for quantitatively examining the amount of attention assigned during deep feature refinement, hence help better interpret a trained model. Using EEGNet as the backbone model, extensive experiments are conducted on the SEED dataset to assess the module's performance on within-subject classification tasks compared to other SOTA attention modules. Requiring only one extra parameter, the inserted module is shown to boost the base model's mean prediction accuracy up to more than 1\% across 15 subjects. A key component of the method is the interpretability of solutions, which is addressed using several different techniques, and is included throughout as part of the dependency analysis.
In this work, a parameter-efficient attention module is presented for emotion classification using a limited, or relatively small, number of electroencephalogram (EEG) signals. This module is called the Monotonicity Constrained Attention Module (MCAM) due to its capability of incorporating priors on the monotonicity when converting features' Gram matrices into attention matrices for better feature refinement. Our experiments have shown that MCAM's effectiveness is comparable to state-of-the-art attention modules in boosting the backbone network's performance in prediction while requiring less parameters. Several accompanying sensitivity analyses on trained models' prediction concerning different attacks are also performed. These attacks include various frequency domain filtering levels and gradually morphing between samples associated with multiple labels. Our results can help better understand different modules' behaviour in prediction and can provide guidance in applications where data is limited and are with noises.
Understanding human emotions is a crucial ability for intelligent robots to provide better human-robot interactions. The existing works are limited to trimmed video-level emotion classification, failing to locate the temporal window corresponding to the emotion. In this paper, we introduce a new task, named Temporal Emotion Localization in videos~(TEL), which aims to detect human emotions and localize their corresponding temporal boundaries in untrimmed videos with aligned subtitles. TEL presents three unique challenges compared to temporal action localization: 1) The emotions have extremely varied temporal dynamics; 2) The emotion cues are embedded in both appearances and complex plots; 3) The fine-grained temporal annotations are complicated and labor-intensive. To address the first two challenges, we propose a novel dilated context integrated network with a coarse-fine two-stream architecture. The coarse stream captures varied temporal dynamics by modeling multi-granularity temporal contexts. The fine stream achieves complex plots understanding by reasoning the dependency between the multi-granularity temporal contexts from the coarse stream and adaptively integrates them into fine-grained video segment features. To address the third challenge, we introduce a cross-modal consensus learning paradigm, which leverages the inherent semantic consensus between the aligned video and subtitle to achieve weakly-supervised learning. We contribute a new testing set with 3,000 manually-annotated temporal boundaries so that future research on the TEL problem can be quantitatively evaluated. Extensive experiments show the effectiveness of our approach on temporal emotion localization. The repository of this work is at https://github.com/YYJMJC/Temporal-Emotion-Localization-in-Videos.
Speech transcription, emotion recognition, and language identification are usually considered to be three different tasks. Each one requires a different model with a different architecture and training process. We propose using a recurrent neural network transducer (RNN-T)-based speech-to-text (STT) system as a common component that can be used for emotion recognition and language identification as well as for speech recognition. Our work extends the STT system for emotion classification through minimal changes, and shows successful results on the IEMOCAP and MELD datasets. In addition, we demonstrate that by adding a lightweight component to the RNN-T module, it can also be used for language identification. In our evaluations, this new classifier demonstrates state-of-the-art accuracy for the NIST-LRE-07 dataset.
Emotion Recognition in Conversation (ERC) plays a significant part in Human-Computer Interaction (HCI) systems since it can provide empathetic services. Multimodal ERC can mitigate the drawbacks of uni-modal approaches. Recently, Graph Neural Networks (GNNs) have been widely used in a variety of fields due to their superior performance in relation modeling. In multimodal ERC, GNNs are capable of extracting both long-distance contextual information and inter-modal interactive information. Unfortunately, since existing methods such as MMGCN directly fuse multiple modalities, redundant information may be generated and diverse information may be lost. In this work, we present a directed Graph based Cross-modal Feature Complementation (GraphCFC) module that can efficiently model contextual and interactive information. GraphCFC alleviates the problem of heterogeneity gap in multimodal fusion by utilizing multiple subspace extractors and Pair-wise Cross-modal Complementary (PairCC) strategy. We extract various types of edges from the constructed graph for encoding, thus enabling GNNs to extract crucial contextual and interactive information more accurately when performing message passing. Furthermore, we design a GNN structure called GAT-MLP, which can provide a new unified network framework for multimodal learning. The experimental results on two benchmark datasets show that our GraphCFC outperforms the state-of-the-art (SOTA) approaches.
With the recent proliferation of open textual data on social media platforms, Emotion Detection (ED) from Text has received more attention over the past years. It has many applications, especially for businesses and online service providers, where emotion detection techniques can help them make informed commercial decisions by analyzing customers/users' feelings towards their products and services. In this study, we introduce ArmanEmo, a human-labeled emotion dataset of more than 7000 Persian sentences labeled for seven categories. The dataset has been collected from different resources, including Twitter, Instagram, and Digikala (an Iranian e-commerce company) comments. Labels are based on Ekman's six basic emotions (Anger, Fear, Happiness, Hatred, Sadness, Wonder) and another category (Other) to consider any other emotion not included in Ekman's model. Along with the dataset, we have provided several baseline models for emotion classification focusing on the state-of-the-art transformer-based language models. Our best model achieves a macro-averaged F1 score of 75.39 percent across our test dataset. Moreover, we also conduct transfer learning experiments to compare our proposed dataset's generalization against other Persian emotion datasets. Results of these experiments suggest that our dataset has superior generalizability among the existing Persian emotion datasets. ArmanEmo is publicly available for non-commercial use at https://github.com/Arman-Rayan-Sharif/arman-text-emotion.
With the improved performance of deep learning, the number of studies trying to apply deep learning to human emotion analysis is increasing rapidly. But even with this trend going on, it is still difficult to obtain high-quality images and annotations. For this reason, the Learning from Synthetic Data (LSD) Challenge, which learns from synthetic images and infers from real images, is one of the most interesting areas. In general, Domain Adaptation methods are widely used to address LSD challenges, but there is a limitation that target domains (real images) are still needed. Focusing on these limitations, we propose a framework Bootstrap Your Emotion Latent (BYEL), which uses only synthetic images in training. BYEL is implemented by adding Emotion Classifiers and Emotion Vector Subtraction to the BYOL framework that performs well in Self-Supervised Representation Learning. We train our framework using synthetic images generated from the Aff-wild2 dataset and evaluate it using real images from the Aff-wild2 dataset. The result shows that our framework (0.3084) performs 2.8% higher than the baseline (0.3) on the macro F1 score metric.
In Weak Supervised Learning (WSL), a model is trained over noisy labels obtained from semantic rules and task-specific pre-trained models. Rules offer limited generalization over tasks and require significant manual efforts while pre-trained models are available only for limited tasks. In this work, we propose to utilize prompt-based methods as weak sources to obtain the noisy labels on unannotated data. We show that task-agnostic prompts are generalizable and can be used to obtain noisy labels for different Spoken Language Understanding (SLU) tasks such as sentiment classification, disfluency detection and emotion classification. These prompts could additionally be updated to add task-specific contexts, thus providing flexibility to design task-specific prompts. We demonstrate that prompt-based methods generate reliable labels for the above SLU tasks and thus can be used as a universal weak source to train a weak-supervised model (WSM) in absence of labeled data. Our proposed WSL pipeline trained over prompt-based weak source outperforms other competitive low-resource benchmarks on zero and few-shot learning by more than 4% on Macro-F1 on all of the three benchmark SLU datasets. The proposed method also outperforms a conventional rule based WSL pipeline by more than 5% on Macro-F1.
Facial Expression Recognition is a vital research topic in most fields ranging from artificial intelligence and gaming to Human-Computer Interaction (HCI) and Psychology. This paper proposes a hybrid model for Facial Expression recognition, which comprises a Deep Convolutional Neural Network (DCNN) and Haar Cascade deep learning architectures. The objective is to classify real-time and digital facial images into one of the seven facial emotion categories considered. The DCNN employed in this research has more convolutional layers, ReLU Activation functions, and multiple kernels to enhance filtering depth and facial feature extraction. In addition, a haar cascade model was also mutually used to detect facial features in real-time images and video frames. Grayscale images from the Kaggle repository (FER-2013) and then exploited Graphics Processing Unit (GPU) computation to expedite the training and validation process. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. The experimental results show a significantly improved classification performance compared to state-of-the-art (SoTA) experiments and research. Also, compared to other conventional models, this paper validates that the proposed architecture is superior in classification performance with an improvement of up to 6%, totaling up to 70% accuracy, and with less execution time of 2098.8s.
Emotion classification of speech and assessment of the emotion strength are required in applications such as emotional text-to-speech and voice conversion. The emotion attribute ranking function based on Support Vector Machine (SVM) was proposed to predict emotion strength for emotional speech corpus. However, the trained ranking function doesn't generalize to new domains, which limits the scope of applications, especially for out-of-domain or unseen speech. In this paper, we propose a data-driven deep learning model, i.e. StrengthNet, to improve the generalization of emotion strength assessment for seen and unseen speech. This is achieved by the fusion of emotional data from various domains. We follow a multi-task learning network architecture that includes an acoustic encoder, a strength predictor, and an auxiliary emotion predictor. Experiments show that the predicted emotion strength of the proposed StrengthNet is highly correlated with ground truth scores for both seen and unseen speech. We release the source codes at: https://github.com/ttslr/StrengthNet.
Transfer learning has been widely used in natural language processing through deep pretrained language models, such as Bidirectional Encoder Representations from Transformers and Universal Sentence Encoder. Despite the great success, language models get overfitted when applied to small datasets and are prone to forgetting when fine-tuned with a classifier. To remedy this problem of forgetting in transferring deep pretrained language models from one domain to another domain, existing efforts explore fine-tuning methods to forget less. We propose DeepEmotex an effective sequential transfer learning method to detect emotion in text. To avoid forgetting problem, the fine-tuning step is instrumented by a large amount of emotion-labeled data collected from Twitter. We conduct an experimental study using both curated Twitter data sets and benchmark data sets. DeepEmotex models achieve over 91% accuracy for multi-class emotion classification on test dataset. We evaluate the performance of the fine-tuned DeepEmotex models in classifying emotion in EmoInt and Stimulus benchmark datasets. The models correctly classify emotion in 73% of the instances in the benchmark datasets. The proposed DeepEmotex-BERT model outperforms Bi-LSTM result on the benchmark datasets by 23%. We also study the effect of the size of the fine-tuning dataset on the accuracy of our models. Our evaluation results show that fine-tuning with a large set of emotion-labeled data improves both the robustness and effectiveness of the resulting target task model.
Accomplishments in the field of artificial intelligence are utilized in the advancement of computing and making of intelligent machines for facilitating mankind and improving user experience. Emotions are rudimentary for people, affecting thinking and ordinary exercises like correspondence, learning and direction. Speech emotion recognition is domain of interest in this regard and in this work, we propose a novel mel spectrogram learning approach in which our model uses the datapoints to learn emotions from the given wav form voice notes in the popular CREMA-D dataset. Our model uses log mel-spectrogram as feature with number of mels = 64. It took less training time compared to other approaches used to address the problem of emotion speech recognition.
In this project, we tackle emotion classification for the Greek language, presenting and releasing a new dataset in Greek. We fine-tune and assess Transformer-based masked language models that were pre-trained on monolingual and multilingual resources, and we present the results per emotion and by aggregating at the sentiment and subjectivity level. The potential of the presented resources is investigated by detecting and studying the emotion of `disgust' in the Greek Parliament records. We: (a) locate the months with the highest values from 1989 to present, (b) rank the Greek political parties based on the presence of this emotion in their speeches, and (c) study the emotional context shift of words used to stigmatise people.
In human contact, emotion is very crucial. Attributes like words, voice intonation, facial expressions, and kinesics can all be used to portray one's feelings. However, brain-computer interface (BCI) devices have not yet reached the level required for emotion interpretation. With the rapid development of machine learning algorithms, dry electrode techniques, and different real-world applications of the brain-computer interface for normal individuals, emotion categorization from EEG data has recently gotten a lot of attention. Electroencephalogram (EEG) signals are a critical resource for these systems. The primary benefit of employing EEG signals is that they reflect true emotion and are easily resolved by computer systems. In this work, EEG signals associated with good, neutral, and negative emotions were identified using channel selection preprocessing. However, researchers had a limited grasp of the specifics of the link between various emotional states until now. To identify EEG signals, we used discrete wavelet transform and machine learning techniques such as recurrent neural network (RNN) and k-nearest neighbor (kNN) algorithm. Initially, the classifier methods were utilized for channel selection. As a result, final feature vectors were created by integrating the features of EEG segments from these channels. Using the RNN and kNN algorithms, the final feature vectors with connected positive, neutral, and negative emotions were categorized independently. The classification performance of both techniques is computed and compared. Using RNN and kNN, the average overall accuracies were 94.844 % and 93.438 %, respectively.
Document-level relation extraction (RE) aims at extracting relations among entities expressed across multiple sentences, which can be viewed as a multi-label classification problem. In a typical document, most entity pairs do not express any pre-defined relation and are labeled as "none" or "no relation". For good document-level RE performance, it is crucial to distinguish such none class instances (entity pairs) from those of pre-defined classes (relations). However, most existing methods only estimate the probability of pre-defined relations independently without considering the probability of "no relation". This ignores the context of entity pairs and the label correlations between the none class and pre-defined classes, leading to sub-optimal predictions. To address this problem, we propose a new multi-label loss that encourages large margins of label confidence scores between each pre-defined class and the none class, which enables captured label correlations and context-dependent thresholding for label prediction. To gain further robustness against positive-negative imbalance and mislabeled data that could appear in real-world RE datasets, we propose a margin regularization and a margin shifting technique. Experimental results demonstrate that our method significantly outperforms existing multi-label losses for document-level RE and works well in other multi-label tasks such as emotion classification when none class instances are available for training.
Emotional expressions are inherently multimodal -- integrating facial behavior, speech, and gaze -- but their automatic recognition is often limited to a single modality, e.g. speech during a phone call. While previous work proposed crossmodal emotion embeddings to improve monomodal recognition performance, despite its importance, an explicit representation of gaze was not included. We propose a new approach to emotion recognition that incorporates an explicit representation of gaze in a crossmodal emotion embedding framework. We show that our method outperforms the previous state of the art for both audio-only and video-only emotion classification on the popular One-Minute Gradual Emotion Recognition dataset. Furthermore, we report extensive ablation experiments and provide detailed insights into the performance of different state-of-the-art gaze representations and integration strategies. Our results not only underline the importance of gaze for emotion recognition but also demonstrate a practical and highly effective approach to leveraging gaze information for this task.
This paper describes the approach to the Emotion Classification shared task held at WASSA 2022 by team PVGs AI Club. This Track 2 sub-task focuses on building models which can predict a multi-class emotion label based on essays from news articles where a person, group or another entity is affected. Baseline transformer models have been demonstrating good results on sequence classification tasks, and we aim to improve this performance with the help of ensembling techniques, and by leveraging two variations of emotion-specific representations. We observe better results than our baseline models and achieve an accuracy of 0.619 and a macro F1 score of 0.520 on the emotion classification task.