A5015709853- Topic Modeling
- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Natural Language Processing Techniques
- Complex Network Analysis Techniques
- Text and Document Classification Technologies
- Biomedical Text Mining and Ontologies
- Multimodal Machine Learning Applications
- Machine Learning in Bioinformatics
- Computational and Text Analysis Methods
- Web Data Mining and Analysis
- Mosquito-borne diseases and control
- Misinformation and Its Impacts
- Spam and Phishing Detection
- Expert finding and Q&A systems
- Speech and dialogue systems
- Opinion Dynamics and Social Influence
- Semantic Web and Ontologies
- Bioinformatics and Genomic Networks
- Recommender Systems and Techniques
- Handwritten Text Recognition Techniques
- Data Mining Algorithms and Applications
- Computational Drug Discovery Methods
- Bayesian Modeling and Causal Inference
- Malaria Research and Control
The Alan Turing Institute
2021-2024
University of Warwick
2018-2024
King's College London
2022-2024
Turing Institute
2022-2024
Southeast University
2014-2023
Ministry of Education of the People's Republic of China
2021-2023
Southern Medical University
2019-2022
South China Normal University
2022
Aston University
2013-2021
Xiangnan University
2021
Sentiment analysis or opinion mining aims to use automated tools detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework based on Latent Dirichlet Allocation (LDA), called joint sentiment/topic model (JST), which detects sentiment topic simultaneously from Unlike other machine learning approaches classification often require labeled corpora for classifier training, the proposed JST is fully...
Abstract IL-17 is a newly described, T cell-derived cytokine with ill-defined physiologic properties. As such, we examined the release of proinflammatory mediators by human macrophages in response to recombinant (rh) IL-17. IL-1β and TNF-α expression synthesis were up-regulated rhIL-17 dose (ED50 was 50 ± 9 ng/ml)- time-dependent fashion, accumulation reaching zenith after h. Release IL-6, PGE2, IL-10, IL-12, IL-1R antagonist, stromelysin also stimulated rhIL-17. mRNA levels controlled...
Different types of sentences express sentiment in very different ways. Traditional sentence-level classification research focuses on one-technique-fits-all solution or only centers one special type sentences. In this paper, we propose a divide-and-conquer approach which first classifies into types, then performs analysis separately from each type. Specifically, find that tend to be more complex if they contain targets. Thus, apply neural network based sequence model classify opinionated...
Sentiment analysis or opinion mining aims to use automated tools detect subjective information such as opinions, attitudes, and feelings expressed in text. This paper proposes a novel probabilistic modeling framework called joint sentiment-topic (JST) model based on latent Dirichlet allocation (LDA), which detects sentiment topic simultaneously from A reparameterized version of the JST Reverse-JST, obtained by reversing sequence generation process, is also studied. Although equivalent...
Research into cyberbullying detection has increased in recent years, due part to the proliferation of across social media and its detrimental effect on young people. A growing body work is emerging automated approaches detection. These utilise machine learning natural language processing techniques identify characteristics a exchange automatically detect by matching textual data identified traits. In this paper, we present systematic review published research (as via Scopus, ACM IEEE Xplore...
In recent years, the boundaries between e-commerce and social networking have become increasingly blurred. Many Web sites support mechanism of login where users can sign on using their network identities such as Facebook or Twitter accounts. Users also post newly purchased products microblogs with links to product pages. this paper, we propose a novel solution for cross-site cold-start recommendation, which aims recommend from at in "cold-start" situations, problem has rarely been explored...
Emotion cause extraction aims to identify the reasons behind a certain emotion expressed in text. It is much more difficult task compared classification. Inspired by recent advances using deep memory networks for question answering (QA), we propose new approach which considers identification as reading comprehension QA. convolutional neural networks, mechanism store relevant context different slots model information. Our proposed can extract both word level sequence features and lexical...
Lixing Zhu, Gabriele Pergola, Lin Gui, Deyu Zhou, Yulan He. Proceedings of the 59th Annual Meeting Association for Computational Linguistics and 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
Bin Liang, Chenwei Lou, Xiang Li, Min Yang, Lin Gui, Yulan He, Wenjie Pei, Ruifeng Xu. Proceedings of the 60th Annual Meeting Association for Computational Linguistics (Volume 1: Long Papers). 2022.
The p38 MAPK mediates transcriptional and post-transcriptional control of cyclooxygenase-2 (COX-2) mRNA following interleukin-1(IL-1)/lipopolysaccharide cellular activation. We explored a positive feedback, prostaglandin E2 (PGE2)-dependent stabilization COX-2 mediated by the cascade in IL-1β-stimulated human synovial fibroblasts. observed rapid (5 min), massive (>30-fold), sustained (>48 h) increase mRNA, protein, PGE2 release recombinant (rh) IL-1β signal that was inhibited NS-398,...
Stance classification, which aims at detecting the stance expressed in text towards a specific target, is an emerging problem sentiment analysis. A major difference between classification and traditional aspect-level that identification of dependent on target might not be explicitly mentioned text. This indicates apart from content, information important to detection. To this end, we propose neural network-based model, incorporates target-specific into by following novel attention mechanism....
Product recommender systems are often deployed by e-commerce websites to improve user experience and increase sales. However, recommendation is limited the product information hosted in those sites only triggered when users performing activities. In this paper, we develop a novel system called METIS, MErchanT Intelligence System, which detects users' purchase intents from their microblogs near real-time makes based on matching demographic extracted public profiles with demographics learned...
In product reviews, it is observed that the distribution of polarity ratings over reviews written by different users or evaluated based on products are often skewed in real world. As such, incorporating user and information would be helpful for task sentiment classification reviews. However, existing approaches ignored temporal nature posted same product. We argue relations might potentially useful learning embedding thus propose employing a sequence model to embed these into representations...
Miles Osborne, Sean Moran, Richard McCreadie, Alexander Von Lunen, Martin Sykora, Elizabeth Cano, Neil Ireson, Craig Macdonald, Iadh Ounis, Yulan He, Tom Jackson, Fabio Ciravegna, Ann O’Brien. Proceedings of 52nd Annual Meeting the Association for Computational Linguistics: System Demonstrations. 2014.
DNA-binding proteins play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. Identification of is one the major challenges field genome annotation. There have been several computational methods proposed literature deal with protein identification. However, most them can't provide an invaluable knowledge base for our understanding DNA-protein interactions. We firstly presented new sequence encoding method called PSSM...