Article
Computer Science, Artificial Intelligence
Anping Zhao, Yu Yu
Summary: The knowledge-enabled language representation model BERT proposed in this work enhances aspect-based sentiment analysis by injecting domain knowledge and leveraging an external sentiment knowledge graph, resulting in more accurate and explainable results.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
P. D. Mahendhiran, Kannimuthu Subramanian
Summary: This article introduces the CLSA-CapsNet method for extracting concepts from natural language text and applies it to hotel reviews dataset. The results demonstrate excellent performance of the model.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Bin Liang, Hang Su, Lin Gui, Erik Cambria, Ruifeng Xu
Summary: This paper proposes a graph convolutional network model Sentic GCN based on SenticNet to enhance the affective dependencies of sentences for aspect-based sentiment analysis. By integrating emotional knowledge from SenticNet, the model effectively handles contextual affective information in sentences, improving the effectiveness of sentiment polarity detection towards specific aspects.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Mathematics
Haibo Yu, Guojun Lu, Qianhua Cai, Yun Xue
Summary: ALSC is a fine-grained task in NLP that aims to identify sentiment towards a given aspect. Current research focuses on integrating semantic, syntactic, and external knowledge for improved accuracy. This paper proposes a novel method that effectively combines these three types of information and achieves high accuracy in experiments.
Article
Computer Science, Artificial Intelligence
Alireza Ghorbanali, Mohammad Karim Sohrabi
Summary: "Sentiment analysis plays a vital role in natural language processing with wide-ranging applications. The rise of social media and its associated tools and technologies has led to the sharing of multimodal content and opinions in various media forms, including text, images, videos, audio, and emojis. Compared to single-modal data, multimodal data contain more valuable information for understanding users' real sentiments. Deep learning-based approaches have emerged to address the challenges of multimodal sentiment analysis, such as incomplete data, heterogeneity of modalities, fusion methods, and interactions between modals. This paper provides a comprehensive survey of sentiment analysis approaches, challenges, applications, and trends, with a particular focus on deep learning-based multimodal sentiment analysis methods."
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Review
Computer Science, Information Systems
Yuehua Zhao, Linyi Zhang, Chenxi Zeng, Wenrui Lu, Yidan Chen, Tao Fan
Summary: This study utilizes a double-layer domain ontology for aspect-level sentiment analysis of online medical reviews. A double-layer aspect recognition model is built, and an object-aspect-sentiment knowledge graph is constructed, providing reference and guidance to sentiment analysis research in the online medical review domain.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Yabing Wang, Guimin Huang, Jun Li, Hui Li, Ya Zhou, Hua Jiang
Summary: This paper introduces the concept of sentiment concept and achieves accurate embedding of sentiment information for words by constructing a multi-semantics sentiment intensity lexicon. It provides more accurate semantics and sentiment representation for words by combining two refined word embeddings methods.
Article
Computer Science, Information Systems
Yongqiang Zheng, Xia Li, Jian-Yun Nie
Summary: Previous studies have shown that incorporating sentiment knowledge is effective for aspect-based sentiment analysis. However, the existing methods only use sentiment knowledge to create static features, which lack the ability to propagate sentiment information over the entire corpus. In this study, we propose a mechanism that can fuse sentiment knowledge at the corpus level and enable the model to better understand the sentiment information of opinion words in the dataset.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Haiyan Wu, Chaogeng Huang, Shengchun Deng
Summary: Aspect-based sentiment analysis (ABSA) aims to extract sentiment-target pairs in review sentences. Previous methods based on recurrent neural networks (RNNs) struggle with accurately capturing sentiment pairs. Recent research incorporates dependency information into structured models, achieving better results, while ignoring domain knowledge related to entities in the comments. This paper proposes a Knowledge-aware Dependency Graph Network (KDGN) that incorporates domain knowledge, dependency labels, and syntax path, showing significant improvement on the ABSA task.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Hao Yan, Benshun Yi, Huixin Li, Danqing Wu
Summary: In this paper, a sentiment knowledge-based bidirectional encoder representation from transformers (SK-BERT) is proposed to overcome the limitations of existing models in sentiment analysis. Experimental results show that the proposed SK-BERT model outperforms other state-of-the-art models in accuracy.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Guojun Lu, Haibo Yu, Zehao Yan, Yun Xue
Summary: Attention-and graph-based models are commonly used in aspect-level sentiment classification tasks. However, most studies neglect the commonsense knowledge of aspects. This paper proposes a novel commonsense knowledge graph-based adapter (CKGA) that can improve the performance of existing models by incorporating external knowledge. Experimental results show that CKGA significantly enhances state-of-the-art aspect-level sentiment classification models.
Article
Computer Science, Information Systems
Tian Shi, Xuchao Zhang, Ping Wang, Chandan K. Reddy
Summary: This study introduces an explanation method that captures causal relationships between keywords and model predictions by learning the importance of keywords for predicted labels across a training corpus based on attention weights. It can automatically learn higher-level concepts and their importance to model prediction tasks.
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
(2022)
Article
Computer Science, Artificial Intelligence
Sarah A. Abdu, Ahmed H. Yousef, Ashraf Salem
Summary: This research provides a comprehensive overview of the latest updates in the field of video sentiment analysis, categorizing thirty-five state-of-the-art models based on the architecture used in each model. It concludes that the most powerful architecture in multimodal sentiment analysis task is the Multi-Modal Multi-Utterance based architecture.
INFORMATION FUSION
(2021)
Article
Computer Science, Information Systems
Yufei Zeng, Zhixin Li, Zhenbin Chen, Huifang Ma
Summary: Deep learning methods based on syntactic dependency trees have achieved great success in Aspect-based Sentiment Analysis (ABSA). However, the lack of accuracy in dependency parsers may cause aspect words to be separated from related opinion words. Additionally, few models incorporate external affective knowledge in ABSA. To address these limitations, we propose a novel architecture that fills the gap in using heterogeneous graph convolution networks for ABSA, by employing affective knowledge to enhance word representation and constructing a heterogeneous graph based on dependency trees. Our proposed method, the Semantic-HGCN, achieves state-of-the-art performance in sentiment prediction according to extensive experiments on multiple datasets.
FRONTIERS OF COMPUTER SCIENCE
(2023)
Article
Computer Science, Information Systems
Xingxin Ye, Yang Xu, Mengshi Luo
Summary: This study introduces a new aspect-level sentiment analysis model named ALBERTC-CNN, which combines different network advantages to improve emotion classification accuracy. The model is tested on two datasets and achieves promising results compared with traditional networks.
Article
Computer Science, Artificial Intelligence
Javier Torregrosa, Sergio D'Antonio-Maceiras, Guillermo Villar-Rodriguez, Amir Hussain, Erik Cambria, David Camacho
Summary: Political tensions have increased in Europe since the beginning of the new century, leading to social movements and political changes in various countries. This study examines the political discourse and underlying tensions during Madrid's elections in May 2021, using a mixed methodology approach. The findings suggest that the electoral campaign is not as negative as perceived by the citizens, and that ideologically extreme parties tend to use more aggressive language.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Wei Sun, Shaoxiong Ji, Erik Cambria, Pekka Marttinen
Summary: Human coders assign standardized medical codes to clinical documents, but it is prone to errors and requires significant effort. Automated medical coding methods using machine learning, such as deep neural networks, have been developed. However, challenges still exist due to code association complexity, noise in lengthy documents, and imbalanced class problem. In this study, we propose a novel neural network model called the Multitask Balanced and Recalibrated Neural Network to address these issues. Experiments on a real-world clinical dataset called MIMIC-III demonstrate that our model outperforms competitive baselines.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Erik Cambria, Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani
Summary: The field of explainable artificial intelligence (XAI) has gained increasing importance in recent years. However, existing research often overlooks the role of natural language in generating explanations. This survey reviews 70 XAI papers published between 2006 and 2021 and evaluates their readiness in terms of natural language explanations. The results show that only a few recent studies have considered using natural language for communication with end users or implemented methods for generating natural language explanations.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Cybernetics
Anton Batliner, Michael Neumann, Felix Burkhardt, Alice Baird, Sarina Meyer, Ngoc Thang Vu, Bjorn W. Schuller
Summary: This paper discusses ethical awareness for paralinguistic applications and proposes taxonomies for data representations, system designs, and applications, as well as for users/test sets and subject areas. By describing and exemplifying the characteristics and interdependencies of these taxonomies, it enables the assessment of ethical constellations.
INTERNATIONAL JOURNAL OF HUMAN-COMPUTER INTERACTION
(2023)
Article
Computer Science, Artificial Intelligence
Seham Basabain, Erik Cambria, Khalid Alomar, Amir Hussain
Summary: An increasing number of studies are using pre-trained language models to tackle few/zero-shot text classification problems. However, most of these studies fail to consider the semantic information embedded in the natural language class labels. This work demonstrates how label information can be leveraged to enhance feature representation in input texts, particularly in scenarios with scarce data resources and short texts lacking semantic information like tweets. The study also shows the effectiveness of zero-shot implementation in predicting new classes across different domains, achieving high accuracy in Arabic sarcasm detection.
Article
Computer Science, Artificial Intelligence
Zhaoxia Wang, Zhenda Hu, Fang Li, Seng-Beng Ho, Erik Cambria
Summary: This research proposes a 3-phase hybrid model that utilizes both technical indicators and social media text sentiments as influence factors for stock trending prediction. The result shows that the proposed method has an accuracy of 73.41% and F1-score of 84.19%. The research not only demonstrates the merits of the proposed method, but also indicates that integrating social opinions with technical indicators is a right direction for enhancing the performance of learning-based stock market trending analysis methods.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Lukas Stappen, Alice Baird, Lea Schumann, Bjoern Schuller
Summary: Truly real-life data presents a challenge for sentiment and emotion research. The large variety of 'in-the-wild' properties necessitates the use of large datasets for building robust machine learning models. This paper introduces MuSe-CaR, a first-ever multimodal dataset, and provides a comprehensive overview of its collection and annotation. Furthermore, the paper proposes a Multi-Head-Attention network that outperforms the baseline model in predicting trustworthiness levels.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Maurice Gerczuk, Shahin Amiriparian, Sandra Ottl, Bjorn W. W. Schuller
Summary: This manuscript discusses the topic of multi-corpus Speech Emotion Recognition (SER) from a deep transfer learning perspective. A large corpus called EMOSET is created by assembling emotional speech data from various existing SER corpora. A novel framework called EMONET is developed using a combination of deep ResNet architecture and residual adapters for multi-corpus SER on EMOSET. The introduced residual adapter approach enables efficient training of a multi-domain SER model and leads to improved performance for the majority of the corpora in EMOSET.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Cybernetics
Guihua Tian, Kun Qian, Xinyi Li, Mengkai Sun, Hao Jiang, Wanyong Qiu, Xiaoming Xie, Zhonghao Zhao, Liangqing Huang, Siyan Luo, Tianxing Guo, Ran Cai, Zhihua Wang, Bjoern W. Schuller
Summary: Intelligent traditional Chinese medicine (ITCM) is an emerging interdisciplinary subject that combines traditional Chinese medicine (TCM) fundamentals and artificial intelligence technologies to promote efficient and precise disease prevention, treatment, and health management in TCM clinical practice. It is currently experiencing significant growth. However, a comprehensive discussion on the benefits of a holistic view in ITCM is lacking.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mostafa M. Amin, Erik Cambria, Bjoern W. Schuller
Summary: The employment of foundation models is expanding and ChatGPT has the potential to enhance existing NLP techniques with its novel knowledge.
IEEE INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wei Li, Yang Li, Vlad Pandelea, Mengshi Ge, Luyao Zhu, Erik Cambria
Summary: The paper introduces a new task called emotion-cause pair extraction in conversations (ECPEC), which aims to extract pairs of emotional utterances and corresponding cause utterances in conversations. The utterance-level ECPEC task is more challenging as the distance between emotion and cause utterances is greater. The experimental results on the proposed ConvECPE dataset demonstrate the feasibility of the ECPEC task and the effectiveness of the framework.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Dazhi Jiang, Runguo Wei, Jintao Wen, Geng Tu, Erik Cambria
Summary: Emotion recognition in conversations has wide applications in various fields. We propose an AutoML strategy based on emotion congruent effect to select suitable knowledge and models, and effectively capture context information and enhance external knowledge in conversations.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Zhengxin Joseph Ye, Bjoern W. Schuller
Summary: Research on algorithmic trading using reinforcement learning has gained popularity in recent years. In this paper, we propose a trading model that aims to align machine trading agents with human traders. We introduce a novel multi-loss function combining supervised learning, single-step and multi-step Q learning, and incorporate imitation learning in the training and trading processes. Our model outperforms baseline models and justifies the inclusion of individual model features to align with human trader behavior.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Jiaming Cheng, Ruiyu Liang, Li Zhao, Chengwei Huang, Bjorn W. Schuller
Summary: In this letter, a metric generative adversarial framework based on a frequency-time convolution recurrent network is proposed for joint noise reduction and hearing loss compensation. Experimental results show that this method can better reduce noise and compensate for hearing loss compared with other algorithms.
IEEE SIGNAL PROCESSING LETTERS
(2023)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)