相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Chemistry, Multidisciplinary
Bayode Ogunleye et al.
Summary: Topic modelling is a crucial task in various applications, and traditional approaches like LDA have shown good performance but lack consistency due to data sparseness and inability to understand word order. This study introduces the use of KernelPCA and K-means clustering in the BERTopic architecture, which produced coherent topics with a high coherence score of 0.8463 when applied to a new dataset of tweets from Nigerian bank customers.
APPLIED SCIENCES-BASEL
(2023)
Article
Biology
Rosario Catelli et al.
Summary: The paper presents a method that combines Natural Language Processing (NLP) and Sentiment Analysis (SA) to analyze sentiments and opinions on COVID-19 vaccination in Italy. The study focuses on a dataset of vaccine-related tweets published between January 2021 and February 2022. By filtering out irrelevant tweets, a total of 353,217 tweets were analyzed. The approach categorizes opinion holders into four classes (Common users, Media, Medicine, Politics) and utilizes NLP tools and domain-specific lexicons to enhance sentiment analysis. The results show an overall negative sentiment, especially among Common users, and different attitudes towards specific events during the examined period.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Engineering, Multidisciplinary
Nikhil Chandran et al.
Summary: TopicStriKer is a model that combines unsupervised topic modeling with supervised string kernels for text classification tasks. It reduces the document corpus using co-occurring topic words and topic proportions per document, and utilizes string kernels for classification, resulting in improved accuracy and reduced training time.
RESULTS IN ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Kenneth Ward Church et al.
Summary: Pursuing state-of-the-art (SOTA) numbers in research papers can have costs, such as missing out on more promising opportunities and potentially leading to unrealistic expectations. Lack of leadership and uncertain reviewing processes are identified as the root causes of SOTA-chasing. This phenomenon is compared to the replication crisis in scientific literature.
NATURAL LANGUAGE ENGINEERING
(2022)
Article
Genetics & Heredity
Malik Yousef et al.
Summary: Medical document classification is a challenging research problem within text classification, and TextNetTopics proposes a novel approach of feature selection based on Bag-of-topics instead of the traditional Bag-of-words. The approach, using the G-S-M method, scores topics to select the top topics for training the classifier, leading to improved accuracy.
FRONTIERS IN GENETICS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Eric Austin et al.
Summary: The popular topic modelling algorithm, Latent Dirichlet Allocation, only produces a simple set of topics. In contrast, the novel algorithm called Community Topic mines communities from word co-occurrence networks to generate topics with a hierarchical structure. Compared to other models, Community Topic uncovers a more coherent topic hierarchy with a tighter relationship between parent and child topics, and it can find this hierarchy more quickly. This algorithm also allows researchers to discover sub- and super-topics on demand, facilitating corpus exploration.
DATA MINING, AUSDM 2022
(2022)
Article
Computer Science, Information Systems
Emil Rijcken et al.
Summary: The article discusses the use of topic models for text classification of clinical notes in predictive tasks and how to select a suitable topic model. The study found that there is no correlation between interpretability and predictive performance, with the proposed fuzzy topic modeling algorithm showing the best interpretability while two state-of-the-art methods perform the best in predictive performance.
FRONTIERS IN BIG DATA
(2022)
Article
Computer Science, Information Systems
Belal Abdullah Hezam Murshed et al.
Summary: This study addresses the issue of poor quality microblog data and proposes a Social Media Data Cleansing Model (SMDCM) to improve data quality for Short-Text Topic Modelling (STTM). By evaluating six topic modelling methods, it was found that GLTM and WNTM were the most effective when applying SMDCM techniques, achieving optimal topic coherence and accuracy values.
Article
Chaitanya Pandey
International Journal of Open Source Software and Processes
(2021)
Article
Chemistry, Multidisciplinary
Quanying Cheng et al.
Summary: Geospatial data plays a crucial role in research and applications across various fields. This paper introduces a new method for topic discovery, which effectively determines development trends and generates coherent topics by assigning literature to different topics. Through this method, text content can be better revealed and new research hotspots can be identified.
APPLIED SCIENCES-BASEL
(2021)
Proceedings Paper
Computer Science, Software Engineering
Christoph Stanik et al.
Summary: On social media platforms, users' comments are valuable but difficult to manage manually. Researchers have proposed automated methods to extract valuable comments and provide insights through topic aggregation. The topic discovery approach using deep natural language processing algorithms achieved high consistency.
29TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE (RE 2021)
(2021)
Review
Computer Science, Information Systems
Yi Guo et al.
Summary: The study identified 7 key areas where AI was applied in COVID-19 research but found a lack of heterogeneous data integration in these applications. Most AI applications adopted a single-sourced approach, potentially leading to biased algorithms.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2021)
Article
Computer Science, Artificial Intelligence
Raffaele Guarasci et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Computer Science, Information Systems
Hamed Jelodar et al.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2020)
Article
Computer Science, Artificial Intelligence
Gibran Fuentes-Pineda et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Article
Computer Science, Information Systems
Korawit Orkphol et al.
Review
Computer Science, Information Systems
Kamran Kowsari et al.
Review
Computer Science, Information Systems
Lijuan Huang et al.
Article
Computer Science, Information Systems
Lijuan Huang et al.
Article
Computer Science, Artificial Intelligence
Juan Carlos Niebles et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2008)
