Article
Computer Science, Information Systems
Ganpat Singh Chauhan, Yogesh Kumar Meena, Dinesh Gopalani, Ravi Nahta
Summary: This paper proposes an unsupervised rule-based method for aspect extraction by adding a sentence coreference resolution step to capture inter-sentence dependencies and pruning out domain irrelevant aspects. Experimental results show that this method outperforms recent supervised deep learning approaches on the SemEval-16 dataset.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Baris Ozyurt, M. Ali Akcayol
Summary: With the widespread use of social networks and other platforms, the volume of user-generated textual data is growing rapidly, making sentiment analysis and opinion mining in user reviews more and more important. To tackle issues like data sparsity and lack of co-occurrence patterns, studies have proposed methods like SS-LDA to adapt LDA for short texts. Experimental results indicate that SS-LDA performs competitively in extracting product aspects.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Fang Chen, Zhongliang Yang, Yongfeng Huang
Summary: This paper proposes a novel multi-task learning framework for end-to-end aspect sentiment triplet extraction (ASTE). By decomposing ASTE into target tagging, opinion tagging, and sentiment tagging subtasks, and utilizing specific tagging schemes, our framework achieves better performance in extracting overlapping triplets and identifying long-range correspondences.
Article
Computer Science, Information Systems
Mengli Zhang, Gang Zhou, Ningbo Huang, Peng He, Wanting Yu, Wenfen Liu
Summary: This work aims to improve the informativeness of opinion summarization by proposing an aspect-augmented model for unsupervised abstractive opinion summarization. The model utilizes reviews without corresponding summaries and enhances the learning ability through a novel cascaded attention mechanism.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Lili Shang, Meiyun Zuo
Summary: In this study, a fused sequential and hierarchical representation (FSHR) model is proposed for extracting aspect terms from opinionated sentences. The model combines sequential and hierarchical representations to capture both linear semantic information for predicting meaning-related aspect terms and syntactic relations for identifying structure-related aspect terms. Experimental results demonstrate that FSHR outperforms competitive baselines, and further analysis reveals the effectiveness of the model.
JOURNAL OF INFORMATION SCIENCE
(2023)
Article
Computer Science, Information Systems
Hyungho Byun, Younhyuk Choi, Chong-Kwon Kim
Summary: This paper proposes a novel scheme called ANES for representation learning and social link inference based on user trajectory data. It extracts behavioral patterns from both trajectory data and the structure of User-POI bipartite graphs, outperforming state-of-the-art baselines in extensive experiments on real-world datasets.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Zusheng Zhang, Yanghui Rao, Hanjiang Lai, Jiahai Wang, Jian Yin
Summary: Aspect extraction is a key task in fine-grained sentiment analysis. This study proposes a CNN-based model that uses dynamic filters generated from aspect information to effectively identify and extract aspects.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Tiankuo Li, Hongji Xu, Zhi Liu, Zheng Dong, Qiang Liu, Juan Li, Shidi Fan, Xiaojie Sun
Summary: With the rapid development of Internet technology and the explosive growth of digital text, opinion mining has become an important research hotspot in the field of natural language processing (NLP). This paper proposes a new deep learning framework for opinion mining, which is shown to outperform other algorithms in terms of performance.
Article
Computer Science, Artificial Intelligence
Avinash Kumar, Pranjal Gupta, Nisarg Kotak, Raghunathan Balan, Lalita Bhanu Murthy Neti, Aruna Malapati
Summary: Aspect category detection is a crucial task in aspect-based sentiment analysis. This paper presents a document clustering approach that focuses on the contextual meaning of words to efficiently detect implicit and explicit aspect categories. A novel BARLAT model is proposed, which utilizes BERT for sentence representation and employs attentive representation learning and adversarial training. Experimental results show that BARLAT outperforms existing models on Restaurant and Laptop datasets.
NEURAL PROCESSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Miguel Lopez, Eugenio Martinez-Camara, M. Victoria Luzon, Francisco Herrera
Summary: The ADOPS methodology focuses on generating structured and explainable opinion summaries through interesting rules, presenting the state of opinions on various aspects of a specific entity to users. Evaluation using the ORCo dataset shows that ADOPS can generate rules with high support and confidence, providing clear and insightful knowledge for users.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Cem Rifki Aydin, Tunga Gungor
Summary: An unsupervised and semi-supervised sentiment analysis method based on antonym word pairs as seeds was developed for Turkish, achieving significant improvements over existing methods. The combination of unsupervised and supervised approaches outperformed other methods, showing the portability of the approaches across languages. Comprehensive analysis of supervised methods and ensemble of classifiers were also conducted to enhance the sentiment analysis results.
NATURAL LANGUAGE ENGINEERING
(2021)
Article
Computer Science, Information Systems
Peijie Sun, Le Wu, Kun Zhang, Yu Su, Meng Wang
Summary: Review based recommendation utilizes users' rating records and associated reviews for recommendation, and provides explanations for recommendation results. However, reviews often lack detailed evaluation, and researchers have used auxiliary information to enrich the generated text. This article explores the generation of more fine-grained explanation text in review based recommendation without using auxiliary data. It addresses the challenges of hidden and unlabeled aspects, as well as injecting aspect information for text generation with noisy review input. Experimental results demonstrate the superiority of the proposed model for recommendation accuracy and explainability.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Eman M. Aboelela, Walaa Gad, Rasha Ismail
Summary: In recent years, many users prefer online shopping, allowing customers to submit comments and feedback on shopping websites. Opinion mining and sentiment analysis are used to assist buyers and sellers in making purchase decisions. A semantic-based aspect level opinion mining (SALOM) model is proposed to consider negation words and other types of product aspects, with promising experimental results.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Haoliang Xiong, Zehao Yan, Chuhan Wu, Guojun Lu, Shiguan Pang, Yun Xue, Qianhua Cai
Summary: ACOS quadruple extraction is a fine-grained sentiment analysis task that aims to extract all ACOS quads in a given sentence. Previous studies use two-stage methods, but they have limitations such as error propagation and ignorance of quad diversity. This work proposes a BART-CRN model that outperforms baseline methods and achieves advanced performances by treating ACOS extraction as a sequence generation task.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Tao Liang, Wenya Wang, Fengmao Lv
Summary: This study proposes a method to improve cross-domain aspect term extraction by leveraging sentence-level aspect category labels. By constructing pivot knowledge for transfer and aligning information at multiple abstraction levels, the approach fully utilizes sentence-level aspect category labels to achieve significant performance gains in extracting aspect terms.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
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, 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
Kai He, Yucheng Huang, Rui Mao, Tieliang Gong, Chen Li, Erik Cambria
Summary: This paper proposes a virtual prompt pre-training method that incorporates the virtual prompt into PLM parameters to achieve entity-relation-aware pre-training. The proposed method provides robust initialization for prompt encoding and avoids the labor-intensive and subjective issues in label word mapping and prompt template engineering.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mostafa Amin, Erik W. Cambria, Bjorn Schuller
Summary: ChatGPT demonstrates the potential of general artificial intelligence capabilities and performs well across various natural language processing tasks. This study evaluates ChatGPT's text classification abilities for affective computing problems including personality prediction, sentiment analysis, and suicide tendency detection. Results show that task-specific RoBERTa models generally outperform other baselines, while ChatGPT performs decently and is comparable to Word2Vec and BoW baselines. ChatGPT exhibits robustness against noisy data, outperforming Word2Vec in such scenarios. The study concludes that ChatGPT is a good generalist model but not as specialized as task-specific models for optimal performance.
IEEE INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mauajama Firdaus, Asif Ekbal, Erik Cambria
Summary: This research proposes a multilingual multitask approach that improves intent accuracy and slot filling for three different languages. The experimental results show an improvement in both tasks for all languages.
INFORMATION FUSION
(2023)
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
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)
Editorial Material
Computer Science, Artificial Intelligence
Frank Xing, Bjoern Schuller, Iti Chaturvedi, Erik Cambria, Amir Hussain
Summary: Neural network-based methods, such as word2vec and GPT-based models, have achieved significant progress in AI research, especially in handling large datasets. However, these methods lack in-depth understanding of the internal features and representations of the data, leading to various problems and concerns.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Kai He, Rui Mao, Tieliang Gong, Chen Li, Erik Cambria
Summary: The study proposes a meta-based self-training method for aspect-based sentiment analysis (ABSA). By generating pseudo-labels and controlling convergence rates, the method improves model performance and accuracy in fine-grained sentiment analysis.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Tan Yue, Rui Mao, Heng Wang, Zonghai Hu, Erik Cambria
Summary: Sarcasm detection is a challenging task in natural language processing, especially in the context of social media where sarcasm is prevalent. This paper proposes a novel model called KnowleNet that incorporates prior knowledge and cross-modal semantic contrast for multimodal sarcasm detection. By leveraging the ConceptNet knowledge base and utilizing contrastive learning, the model achieves state-of-the-art performance on benchmark datasets.
INFORMATION FUSION
(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)
Article
Computer Science, Artificial Intelligence
Jialun Wu, Kai He, Rui Mao, Chen Li, Erik Cambria
Summary: Predicting a patient's future health condition is a trending topic in the intelligent medical field. This paper proposes a knowledge-guided predictive framework called MEGACare, which leverages multi-faceted medical knowledge and multi-view learning to enhance clinical prediction accuracy.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Kai He, Rui Mao, Yucheng Huang, Tieliang Gong, Chen Li, Erik Cambria
Summary: In this paper, a prompt-based contrastive learning method is proposed for few-shot NER tasks. The method leverages external knowledge to initialize semantic anchors and optimizes prompts and sentence embeddings with a proposed semantic-enhanced contrastive loss. The method outperforms traditional contrastive learning methods in few-shot scenarios and effectively addresses the issues in conventional methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
