Article
Computer Science, Information Systems
Abdullah Ali Salamai, Ather Abdulrahman Ageeli, El-Sayed M. El-kenawy
Summary: E-commerce is a system that allows individuals to purchase and sell goods online, aiming to provide convenience to customers by eliminating the need to visit physical stores. This research aims to develop machine learning algorithms for predicting e-commerce sales and tests the proposed algorithm on a time series dataset.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
Junwen Lu, Xinrong Zhan, Xintao Zhan, Lihui Shi
Summary: A new book impact evaluation method based on user rating is proposed to evaluate the influence of book nodes in online social networks. The method is proven to be efficient and accurate through analyzing real review data and comparison experiments with other metrics.
Article
Computer Science, Artificial Intelligence
Ibrahim Erdem Kalkan, Cenk Sahin
Summary: Recommender systems can predict customers' next purchases. This study proposes a hybrid model that handles both sequential and non-sequential features to improve cross-selling effectiveness.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Chen Gao, Chao Huang, Donghan Yu, Haohao Fu, Tzh-Heng Lin, Depeng Jin, Yong Li
Summary: Social commerce transforms social communities into inclusive places for business by incentivizing users to share products with their friends. This article proposes a TriM model that considers both the sharer's influence and the receiver's interest, and improves recommendation performance through joint learning on sparse data.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Review
Chemistry, Multidisciplinary
Sabina-Cristiana Necula, Vasile-Daniel Pavaloaia
Summary: Electronic commerce is closely connected to recommendation processes, which can take various forms such as virtual assistants and real-time online suggestions. Different algorithms and technologies are used for each form, depending on the task at hand. This study investigates the utilization of artificial intelligence in e-commerce recommender systems and explores current and future trends in the field through a systematic literature review and data analysis. The findings reveal that artificial intelligence, combined with other technologies like blockchain, virtual reality, and augmented reality, enhances the consumer experience in the e-commerce process.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Hadis Ahmadian Yazdi, Seyyed Javad Seyyed Mahdavi Chabok, Maryam Kheirabadi
Summary: Compared to traditional classrooms, web-based educational systems face challenges in guiding students to choose appropriate learning resources due to the vast number of online resources available. The proposed resource recommender system integrates deep learning networks to offer more accurate and relevant recommendations based on current and long-term user interests, achieving higher accuracy and improved performance in recommending resources to students.
APPLIED ARTIFICIAL INTELLIGENCE
(2022)
Article
Mathematics, Interdisciplinary Applications
Gonzalo Uribarri, Gabriel B. Mindlin
Summary: Time series forecasting is a significant research problem in the fields of science and engineering, and machine learning algorithms have been proven successful in this area. This paper focuses on training Long Short Term Memory networks (LSTM), a type of Recurrent Neural Networks (RNNs), to predict time series data from a chaotic system. The study shows that LSTM networks can learn to generate a data embedding in their inner state that is topologically equivalent to the original strange attractor.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Computer Science, Artificial Intelligence
Zhi Li, Daichi Amagata, Yihong Zhang, Takuya Maekawa, Takahiro Hara, Kei Yonekawa, Mori Kurokawa
Summary: This study focuses on flash sale recommendations and proposes a meta-learning-based recommender system that can handle users' period-specific preferences and the cold-start problem. Experimental results show significant improvements in flash sale recommendations and most of the non-flash sale cold-start recommendations.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Herman M. Wandabwa, M. Asif Naeem, Farhaan Mirza, Russel Pears
Summary: Consumption of content in short-text microblogs is influenced by individual users and their social network interests, which change dynamically over time. Detecting semantic changes is important for mapping user profiles, especially in platforms with limited user data. A model was used to validate interest changes over time, achieving a high Pearson correlation coefficient for interest change verification.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Amirreza Salamat, Xiao Luo, Ali Jafari
Summary: HeteroGraphRec is a social recommender system that models the social network as a heterogeneous graph and intelligently aggregates information using GNNs with attention mechanisms. Research shows that HeteroGraphRec outperforms top social recommender systems, demonstrating strong robustness and performance superiority.
KNOWLEDGE-BASED SYSTEMS
(2021)
Review
Chemistry, Multidisciplinary
Rand Jawad Kadhim Almahmood, Adem Tekerek
Summary: In recent years, shopping has become challenging due to the COVID-19 pandemic. E-commerce recommendation systems help users find new products and personalize their shopping experience using techniques such as rating, ranking, and reviewing. These systems employ intelligent agents that use AI techniques to model and predict user preferences, reducing search efforts. The study found that deep learning algorithms, such as CNN, RNN, and sentiment analysis, are particularly effective in solving recommendation problems.
APPLIED SCIENCES-BASEL
(2022)
Article
Business
Mi-Tsuen Hsieh, Shie-Jue Lee, Chih-Hung Wu, Chun-Liang Hou, Chen-Sen Ouyang, Zhan-Pei Lin
Summary: This paper discusses the cold-start problem in recommender systems and proposes a hybrid recommender system called ALFNCF to address this issue. ALFNCF combines collaborative filtering, content-based filtering, and neural network technologies, and predicts user ratings for new items based on training on past rating feedback information.
ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS
(2022)
Article
Geosciences, Multidisciplinary
Pinzeng Rao, Yicheng Wang, Fang Wang, Yang Liu, Xiaoya Wang, Zhu Wang
Summary: This study utilized multiple machine learning methods to downscale the coarse spatial resolution SMAP SM products and produce higher-spatial-resolution soil moisture data. The downscaled data showed good performance in assessing soil drought and reversing desertification, indicating its potential for application.
EARTH SYSTEM SCIENCE DATA
(2022)
Article
Computer Science, Information Systems
Cristiana Tudor
Summary: With the increasing reliance on e-commerce and multimedia content after COVID-19, it is crucial for companies to digitize their business methods and models. This study focuses on the US as the global e-commerce market leader and proposes an integrated framework to estimate the impact of the pandemic on e-commerce retail sales and share. The results show significant changes in the trend and structure of the US retail sales sector due to COVID-19, accelerating the growth of the e-commerce sector by at least five years.
Article
Computer Science, Information Systems
Herman Masindano Wandabwa, M. Asif Naeem, Farhaan Mirza, Russel Pears
Summary: Knowledge-based applications like recommender systems in social networks rely on complex social discussions and user connections, with platforms like Twitter being powerful due to real-time content dissemination and intricate user connections. Personalized user profiles based on their interests are essential for personalized third-party content recommendations on the platform.
INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Linhai Zhang, Chao Lin, Deyu Zhou, Yulan He, Meng Zhang
Summary: This study introduces a novel KBQA model based on Bayesian Neural Network to estimate uncertainties from model predictions and data, highlighting the importance of uncertainties for KBQA systems. Experimental results demonstrate the effectiveness of uncertainties in misclassification and error detection tasks, while the proposed model achieves comparable performance on the Simple-Questions dataset.
COMPUTER SPEECH AND LANGUAGE
(2021)
Article
Computer Science, Artificial Intelligence
Deyu Zhou, Kai Sun, Mingqi Hu, Yulan He
Summary: Image generation from text has attracted great attention, and in order to accurately generate images, we propose two novel end-to-end frameworks to incorporate entity information and introduce a new metric to measure the consistency between generated images and corresponding text descriptions.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Rilwan A. Adewoyin, Peter Dueben, Peter Watson, Yulan He, Ritabrata Dutta
Summary: This study presents a Deep Learning approach, TRU-NET, for high-resolution precipitation prediction, which outperforms traditional models and achieves more accurate results. The model architecture and loss function proposed in the study contribute to the improvement in precipitation prediction accuracy across various data formulation strategies.
Review
Computer Science, Artificial Intelligence
Tianyong Hao, Xinxin Li, Yulan He, Fu Lee Wang, Yingying Qu
Summary: This paper provides a systematic review of recent developments in deep learning methods for question answering, covering methods, datasets, and applications, and discussing network structure characteristics, method innovations, and effectiveness. The survey is expected to contribute to summarizing recent research progress and future research directions in deep learning methods for question answering.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Bin Liang, Xiang Li, Lin Gui, Yonghao Fu, Yulan He, Min Yang, Ruifeng Xu
Summary: Existing sentiment analysis methods in aspect-based/category focus successfully detect sentiment polarity towards fixed aspect categories. However, practical applications involve changing aspect categories. Dealing with unseen categories is not fully explored in current methods. In this article, we propose a few-shot aspect category sentiment analysis task and introduce a novel Aspect-Focused Meta-Learning (AFML) framework to effectively predict sentiment polarity of unseen aspect categories.
ACM TRANSACTIONS ON INFORMATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Lin Gui, Leng Jia, Jiyun Zhou, Ruifeng Xu, Yulan He
Summary: This paper proposes a multi-task learning framework that jointly learns a sentiment classifier and a topic model, aiming to make the word-level latent topic distributions in the topic model similar to the word-level attention vectors in sentiment classifiers. The experimental results on Yelp and IMDB datasets demonstrate the superior performance of the proposed framework in both sentiment classification and topic modeling tasks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Software Engineering
Shuzheng Gao, Cuiyun Gao, Yulan He, Jichuan Zeng, Lunyiu Nie, Xin Xia, Michael Lyu
Summary: Code summaries help developers understand programs and save time during software maintenance. Recent studies have used deep learning techniques, such as Transformer-based approaches, to generate accurate code summaries. However, integrating code structure information into Transformers effectively has been under-explored in this task domain.
ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Hanqi Yan, Lin Gui, Yulan He
Summary: In recent years, there has been increasing interest in developing interpretable models in Natural Language Processing (NLP). However, it is difficult to accurately explain model decisions by words or phrases when neural models in NLP compose word semantics hierarchically. This article proposes a novel Hierarchical Interpretable Neural Text classifier, called HINT, which generates explanations of model predictions in the form of label-associated topics. Experimental results show that HINT achieves comparable text classification results and provides better interpretations than other interpretable neural text classifiers.
COMPUTATIONAL LINGUISTICS
(2022)
Article
Computer Science, Information Systems
Elena Kochkina, Tamanna Hossain, Robert L. Logan, Miguel Arana-Catania, Rob Procter, Arkaitz Zubiaga, Sameer Singh, Yulan He, Maria Liakata
Summary: Research on automated social media rumour verification has achieved high performance with neural models, but their generalisability to datasets beyond the ones they were trained on remains unclear. This study aims to fill this gap by assessing the generalisability of top performing neural rumour verification models across different architectures. A novel dataset called COVID-RV is collected and released for a more comprehensive evaluation of model performance. The study finds a significant drop in performance when testing models on different datasets from their training sets. Additionally, the ability of models to generalise in a few-shot learning setup and with updated word embeddings is evaluated.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Jun Wang, Abhir Bhalerao, Yulan He
Summary: This paper proposes a network model called XPRONET, which improves the task of radiology report generation through cross-modal prototype learning and improved multi-label prototype learning. Experimental results demonstrate that XPRONET achieves significant improvements on two benchmarks.
COMPUTER VISION - ECCV 2022, PT XXXV
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Lixing Zhu, Zheng Fang, Gabriele Pergola, Rob Procter, Yulan He
Summary: Building models to detect vaccine attitudes on social media is challenging due to the complexity and limited availability of annotated data. This study proposes a novel semi-supervised approach called VADET, which leverages unannotated data to learn the topical information of the domain, and fine-tunes the model with manually annotated examples. The results demonstrate that VADET outperforms existing models in stance detection and tweet clustering.
NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Rilwan A. Adewoyin, Ritabrata Dutta, Yulan He
Summary: This paper introduces RSTGen, a framework based on Rhetorical Structure Theory (RST), to enhance the cohesion and coherence of long-form text generated by language models. The model demonstrates its ability to control the structural discourse and semantic features of generated text, and performs competitively in argument generation and story generation tasks.
NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Miguel Arana-Catania, Elena Kochkina, Arkaitz Zubiaga, Maria Liakata, Rob Procter, Yulan He
Summary: This study focuses on automated veracity assessment methods, covering from dataset creation to the development of new technologies based on natural language inference, and concentrating on misinformation related to the COVID-19 pandemic. By constructing a novel dataset and proposing automated veracity assessment techniques based on natural language inference, these methods have shown competitive advantages in experiments compared to SOTA methods.
NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES
(2022)
Proceedings Paper
Computer Science, Cybernetics
Bin Liang, Zixiao Chen, Lin Gui, Yulan He, Min Yang, Ruifeng Xu
Summary: This paper proposes a framework for zero-shot stance detection that effectively distinguishes the types of stance features and learns transferable features. By treating stance feature type identification as a pretext task and using a hierarchical contrastive learning strategy to capture correlations and differences, the model is able to better represent the stance of previously unseen targets.
PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
John Dougrez-Lewis, Elena Kochkina, Miguel Arana-Catania, Maria Liakata, Yulan He
Summary: Work on social media rumour verification utilizes signals from posts, propagation, and users, and incorporating external evidence improves the effectiveness of rumour verification models. To support research in this area, a new dataset called PHEMEPlus is released, which includes social media conversations and relevant external evidence for each rumour.
PROCEEDINGS OF THE FIFTH FACT EXTRACTION AND VERIFICATION WORKSHOP (FEVER 2022)
(2022)