Seng-Beng Ho
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Seng-Beng Ho has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Zhaoxia Wang
Singapore Management University
9 shared publications - Erik Cambria
Nanyang technological university, Singapore, Singapore
7 shared publications - Boon-Kiat Quek
Institute of High Performance Computing Agency for Science, Technology and Research Singapore
2 shared publications - Jingfeng Cui
Fujian Normal University, Fuzhou, China
2 shared publications - Xinyue Zhang
East China Normal University
2 shared publications - Zhenda Hu
School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai, China
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 6 January 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58 (3) , 1-37
A review of Chinese sentiment analysis: subjects, methods, and trends
- 6 January 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58 (3) , 1-37
Top Cited PapersOpen AccessA review of Chinese sentiment analysis: subjects, methods, and trends
- 1 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39 (5) , 82-89
Joint Weakly Supervised Image Emotion Analysis Based on Interclass Discrimination and Intraclass Correlation
Regional information-based image emotion analysis has recently garnered significant attention. However, existing methods often focus on identifying region proposals through layered steps or merely rely on visual saliency. These approaches may lead to an underestimation of emotional categories and a lack of comprehensive interclass discrimination perception and emotional intraclass contextual mining. To address these limitations, we propose a novel approach named InterIntraIEA, which combines interclass discrimination and intraclass correlation joint learning capabilities for image emotion analysis. The proposed method not only employs category-specific dictionary learning for class adaptation, but also models intraclass contextual relationships and perceives correlations at the channel level. This refinement process improves interclass descriptive ability and enhances emotional categories, resulting in the production of pseudomaps that provide more precise emotional region information. These pseudomaps, in conjunction with top-level features extracted from a multiscale extractor, are then input into a weakly supervised fusion module to predict emotional sentiment categories.
- 1 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39 (5) , 82-89
Joint Weakly Supervised Image Emotion Analysis Based on Interclass Discrimination and Intraclass Correlation
Regional information-based image emotion analysis has recently garnered significant attention. However, existing methods often focus on identifying region proposals through layered steps or merely rely on visual saliency. These approaches may lead to an underestimation of emotional categories and a lack of comprehensive interclass discrimination perception and emotional intraclass contextual mining. To address these limitations, we propose a novel approach named InterIntraIEA, which combines interclass discrimination and intraclass correlation joint learning capabilities for image emotion analysis. The proposed method not only employs category-specific dictionary learning for class adaptation, but also models intraclass contextual relationships and perceives correlations at the channel level. This refinement process improves interclass descriptive ability and enhances emotional categories, resulting in the production of pseudomaps that provide more precise emotional region information. These pseudomaps, in conjunction with top-level features extracted from a multiscale extractor, are then input into a weakly supervised fusion module to predict emotional sentiment categories.
- 22 May 2024
- Published by Springer Nature
- p. 14-30
Knowledge Representation for Conceptual, Motivational, and Affective Processes in Natural Language Communication
- 22 May 2024
- Published by Springer Nature
- p. 14-30
Knowledge Representation for Conceptual, Motivational, and Affective Processes in Natural Language Communication
- 28 April 2024
- Published by Springer Nature
- p. 95-107
DLVS4Audio2Sheet: Deep Learning-Based Vocal Separation for Audio into Music Sheet Conversion
- 28 April 2024
- Published by Springer Nature
- p. 95-107
DLVS4Audio2Sheet: Deep Learning-Based Vocal Separation for Audio into Music Sheet Conversion
- 8 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 38 (6) , 62-69
Seven Pillars for the Future of Artificial Intelligence
In recent years, artificial intelligence (AI) research has showcased tremendous potential to positively impact humanity and society. Although AI frequently outperforms humans in tasks related to classification and pattern recognition, it continues to face challenges when dealing with complex tasks such as intuitive decision making, sense disambiguation, sarcasm detection, and narrative understanding as these require advanced kinds of reasoning, e.g., common-sense reasoning and causal reasoning, which have not been emulated satisfactorily yet. To address these shortcomings, we propose seven pillars that we believe represent the key hallmark features for the future of AI, namely, multidisciplinarity, task decomposition, parallel analogy, symbol grounding, similarity measure, intention awareness, and trustworthiness.
- 8 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 38 (6) , 62-69
Seven Pillars for the Future of Artificial Intelligence
In recent years, artificial intelligence (AI) research has showcased tremendous potential to positively impact humanity and society. Although AI frequently outperforms humans in tasks related to classification and pattern recognition, it continues to face challenges when dealing with complex tasks such as intuitive decision making, sense disambiguation, sarcasm detection, and narrative understanding as these require advanced kinds of reasoning, e.g., common-sense reasoning and causal reasoning, which have not been emulated satisfactorily yet. To address these shortcomings, we propose seven pillars that we believe represent the key hallmark features for the future of AI, namely, multidisciplinarity, task decomposition, parallel analogy, symbol grounding, similarity measure, intention awareness, and trustworthiness.
- Open Access
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 121-128
Why is that a Good or Not a Good Frying Pan? – Knowledge Representation for Functions of Objects and Tools for Design Understanding, Improvement, and Generation
The understanding of the functional aspects of objects and tools is of paramount importance in supporting an intelligent system in navigating around in the environment and interacting with various objects, structures, and systems, to help fulfil its goals. A detailed understanding of functionalities can also lead to design improvements and novel designs that would enhance the operations of AI and robotic systems on the one hand, and human lives on the other. This paper demonstrates how a particular object - in this case, a frying pan - and its participation in the processes it is designed to support - in this case, the frying process - can be represented in a general function representational language and framework, that can be used to flesh out the processes and functionalities involved, leading to a deep conceptual understanding with explainability of functionalities that allows the system to answer “why” questions - why is something a good frying pan, say, or why a certain part on the frying pan is designed in a certain way? Or, why is something not a good frying pan? This supports the redesign and improvement on design of objects, artifacts, and tools, as well as the potential for generating novel designs that are functionally accurate, usable, and satisfactory.
- 5 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 121-128
Open AccessWhy is that a Good or Not a Good Frying Pan? – Knowledge Representation for Functions of Objects and Tools for Design Understanding, Improvement, and Generation
The understanding of the functional aspects of objects and tools is of paramount importance in supporting an intelligent system in navigating around in the environment and interacting with various objects, structures, and systems, to help fulfil its goals. A detailed understanding of functionalities can also lead to design improvements and novel designs that would enhance the operations of AI and robotic systems on the one hand, and human lives on the other. This paper demonstrates how a particular object - in this case, a frying pan - and its participation in the processes it is designed to support - in this case, the frying process - can be represented in a general function representational language and framework, that can be used to flesh out the processes and functionalities involved, leading to a deep conceptual understanding with explainability of functionalities that allows the system to answer “why” questions - why is something a good frying pan, say, or why a certain part on the frying pan is designed in a certain way? Or, why is something not a good frying pan? This supports the redesign and improvement on design of objects, artifacts, and tools, as well as the potential for generating novel designs that are functionally accurate, usable, and satisfactory.
- 19 April 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (21) , 15907-15921
MiMuSA—mimicking human language understanding for fine-grained multi-class sentiment analysis
- 19 April 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (21) , 15907-15921
MiMuSA—mimicking human language understanding for fine-grained multi-class sentiment analysis
- 9 March 2023
- Published by Springer Nature in Cognitive Computation
- Vol. 15 (3) , 1092-1102
Learning-Based Stock Trending Prediction by Incorporating Technical Indicators and Social Media Sentiment
- 9 March 2023
- Published by Springer Nature in Cognitive Computation
- Vol. 15 (3) , 1092-1102
Learning-Based Stock Trending Prediction by Incorporating Technical Indicators and Social Media Sentiment
- Top Cited PapersOpen Access
- 6 January 2023
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (8) , 8469-8510
Survey on sentiment analysis: evolution of research methods and topics
Sentiment analysis, one of the research hotspots in the natural language processing field, has attracted the attention of researchers, and research papers on the field are increasingly published. Many literature reviews on sentiment analysis involving techniques, methods, and applications have been produced using different survey methodologies and tools, but there has not been a survey dedicated to the evolution of research methods and topics of sentiment analysis. There have also been few survey works leveraging keyword co-occurrence on sentiment analysis. Therefore, this study presents a survey of sentiment analysis focusing on the evolution of research methods and topics. It incorporates keyword co-occurrence analysis with a community detection algorithm. This survey not only compares and analyzes the connections between research methods and topics over the past two decades but also uncovers the hotspots and trends over time, thus providing guidance for researchers. Furthermore, this paper presents broad practical insights into the methods and topics of sentiment analysis, while also identifying technical directions, limitations, and future work.
- 6 January 2023
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (8) , 8469-8510
Top Cited PapersOpen AccessSurvey on sentiment analysis: evolution of research methods and topics
Sentiment analysis, one of the research hotspots in the natural language processing field, has attracted the attention of researchers, and research papers on the field are increasingly published. Many literature reviews on sentiment analysis involving techniques, methods, and applications have been produced using different survey methodologies and tools, but there has not been a survey dedicated to the evolution of research methods and topics of sentiment analysis. There have also been few survey works leveraging keyword co-occurrence on sentiment analysis. Therefore, this study presents a survey of sentiment analysis focusing on the evolution of research methods and topics. It incorporates keyword co-occurrence analysis with a community detection algorithm. This survey not only compares and analyzes the connections between research methods and topics over the past two decades but also uncovers the hotspots and trends over time, thus providing guidance for researchers. Furthermore, this paper presents broad practical insights into the methods and topics of sentiment analysis, while also identifying technical directions, limitations, and future work.
- Open Access
Knowledge Representation for Conceptual, Motivational, and Affective Processes in Natural Language Communication
Natural language communication is an intricate and complex process. The speaker usually begins with an intention and motivation of what is to be communicated, and what effects are expected from the communication, while taking into consideration the listener's mental model to concoct an appropriate sentence. The listener likewise has to interpret what the speaker means, and respond accordingly, also with the speaker's mental state in mind. To do this successfully, conceptual, motivational, and affective processes have to be represented appropriately to drive the language generation and understanding processes. Language processing has succeeded well with the big data approach in applications such as chatbots and machine translation. However, in human-robot collaborative social communication and in using natural language for delivering precise instructions to robots, a deeper representation of the conceptual, motivational, and affective processes is needed. This paper capitalizes on the UGALRS (Unified General Autonomous and Language Reasoning System) framework and the CD+ (Conceptual Representation Plus) representational scheme to illustrate how social communication through language is supported by a knowledge representational scheme that handles conceptual, motivational, and affective processes in a deep and general way. Though a small set of concepts, motivations, and emotions is treated in this paper, its main contribution is in articulating a general framework of knowledge representation and processing to link these aspects together in serving the purpose of natural language communication for an intelligent system.
Open AccessKnowledge Representation for Conceptual, Motivational, and Affective Processes in Natural Language Communication
Natural language communication is an intricate and complex process. The speaker usually begins with an intention and motivation of what is to be communicated, and what effects are expected from the communication, while taking into consideration the listener's mental model to concoct an appropriate sentence. The listener likewise has to interpret what the speaker means, and respond accordingly, also with the speaker's mental state in mind. To do this successfully, conceptual, motivational, and affective processes have to be represented appropriately to drive the language generation and understanding processes. Language processing has succeeded well with the big data approach in applications such as chatbots and machine translation. However, in human-robot collaborative social communication and in using natural language for delivering precise instructions to robots, a deeper representation of the conceptual, motivational, and affective processes is needed. This paper capitalizes on the UGALRS (Unified General Autonomous and Language Reasoning System) framework and the CD+ (Conceptual Representation Plus) representational scheme to illustrate how social communication through language is supported by a knowledge representational scheme that handles conceptual, motivational, and affective processes in a deep and general way. Though a small set of concepts, motivations, and emotions is treated in this paper, its main contribution is in articulating a general framework of knowledge representation and processing to link these aspects together in serving the purpose of natural language communication for an intelligent system.