Review
Computer Science, Artificial Intelligence
Sanaa Kaddoura, Ganesh Chandrasekaran, Daniela Elena Popescu, Jude Hemanth Duraisamy
Summary: The presence of spam content in social media is increasing, making the detection and control of spam text essential for improving social media security. This paper provides a detailed survey on the latest developments in spam text detection and classification, discussing techniques such as Machine Learning, Deep Learning, and text-based approaches, and the challenges encountered in spam identification.
PEERJ COMPUTER SCIENCE
(2022)
Review
Computer Science, Information Systems
Jalal Rezaeenour, Mahnaz Ahmadi, Hamed Jelodar, Roshan Shahrooei
Summary: Text mining is an important method for extracting useful information from unstructured textual data, mainly applied in deep learning and machine learning techniques. The study found that hybrid LSTM is the most commonly used deep learning algorithm, while SVM is the machine learning method with high accuracy.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Review
Computer Science, Information Systems
Raymon van Dinter, Bedir Tekinerdogan, Cagatay Catal
Summary: This study conducts a systematic literature review on the automation of SLR studies, aiming to collect and synthesize the current research in this area for further exploration. The review analyzes 41 primary studies and identifies the objectives, application domains, automated steps, techniques, challenges, and solution directions in SLR automation. The study reveals that while automation approaches for SLR have focused on the selection of primary studies, there is a lack of automation techniques applied in the planning and reporting phases, indicating a need for further research in automating other activities of the SLR process.
INFORMATION AND SOFTWARE TECHNOLOGY
(2021)
Review
Computer Science, Artificial Intelligence
Matin N. Ashtiani, Bijan Raahemi
Summary: Researchers and practitioners have explored the use of textual and numeric data to predict financial markets, with limited attention given to news content. This systematic review focuses on papers that utilize machine learning and text mining techniques to predict the stock market using news. The review identifies gaps and barriers in the field, recommends future research directions, and highlights the growing trend towards using advanced neural networks and language models in stock market prediction.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Information Science & Library Science
Sudha Cheerkoot-Jalim, Kavi Kumar Khedo
Summary: This work presents the results of a systematic literature review on biomedical text mining, identifying different text mining approaches, common tools, and challenges in the field. Researchers primarily utilize data sources such as electronic health records, biomedical literature, social media, and health-related forums for text mining. The most common technique is natural language processing, often using tools like MetaMap and Unstructured Information Management Architecture.
JOURNAL OF KNOWLEDGE MANAGEMENT
(2021)
Review
Computer Science, Information Systems
Li Kong, Chuanyi Li, Jidong Ge, Vincent Ng, Bin Luo
Summary: In recent years, the number of online product reviews has been increasing rapidly, making it difficult for customers to read through all the reviews. To address this issue, researchers propose a new model for predicting review helpfulness, combining Convolutional Neural Network (CNN) and TransE. The experimental results demonstrate that this approach outperforms the state of the art.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2022)
Article
Mathematical & Computational Biology
Toni Lange, Guido Schwarzer, Thomas Datzmann, Harald Binder
Summary: The research project explored the potential of machine learning methods to reduce human workload, evaluated the performance of deep learning methods compared to more established machine learning methods, and highlighted the importance of data preprocessing on the final performance of approaches. Machine learning methods provided reasonable classification, but the final performance heavily relies on data preparation.
RESEARCH SYNTHESIS METHODS
(2021)
Review
Computer Science, Artificial Intelligence
Noratikah Nordin, Zurinahni Zainol, Mohd Halim Mohd Noor, Lai Fong Chan
Summary: This study provides a comprehensive review of the application of machine learning techniques in the prediction of suicidal behavior, summarizing the methods, sample descriptions, sample size, classification tasks, number of features, types of machine learning techniques, and performance evaluation methods of related studies.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Seonghyeon Moon, Gitaek Lee, Seokho Chi
Summary: This research aimed to develop an automated system for reviewing construction specifications by analyzing the different semantic properties using natural language processing techniques. The proposed system showed promising results in reducing time, supplementing reviewer's experience, enhancing accuracy, and achieving consistency, contributing positively to risk management in the construction industry.
ADVANCED ENGINEERING INFORMATICS
(2022)
Review
Computer Science, Artificial Intelligence
Eduardo Tieppo, Roger Robson dos Santos, Jean Paul Barddal, Julio Cesar Nievola
Summary: Research on hierarchical classification and streaming data currently lacks intersection, with studies focusing separately on each area. This study analyzed the characteristics of state-of-the-art works in hierarchical classification for streaming data, identifying problems, datasets, algorithms, evaluation metrics, and research gaps in the field. Results show a need for future research to consider common characteristics shared between hierarchical classification and data stream classification.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Review
Computer Science, Artificial Intelligence
Ning Wang, Jun Yang, Xuefeng Kong, Ying Gao
Summary: With the rapid development of e-commerce, two-dimensional time series analysis has become increasingly important in determining fake reviews. This paper proposes a comprehensive fake review identification framework that combines suspicion degree, review text, and reviewer behavior features, with experimental results demonstrating its effectiveness.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Multidisciplinary Sciences
Gergely Mark Csanyi, Daniel Nagy, Renato Vagi, Janos Pal Vadasz, Tamas Orosz
Summary: Data sharing in judicial systems can enhance transparency, but the sensitive information in legal documents must be anonymized to prevent privacy breaches. Named Entity Recognition methods, machine learning, and anonymization models like differential privacy are crucial for reducing re-identification risk.Preserving the utility of the text while anonymizing legal documents is essential.
Review
Education & Educational Research
Nabila Sghir, Amina Adadi, Mohammed Lahmer
Summary: In recent years, there has been a rise in the use of Machine and Deep learning models to predict academic outcomes based on student-related data, aiming to improve the learning process. This study reviews the latest research on Predictive Analytics in Higher Education, analyzing outcomes frequently predicted, learning features used, predictive modelling process, and key performance metrics. The study also identifies gaps in current literature and suggests future research directions. It serves as a comprehensive reference for researchers in the field and informs educational stakeholders and decision-makers about potential opportunities.
EDUCATION AND INFORMATION TECHNOLOGIES
(2023)
Review
Computer Science, Interdisciplinary Applications
Frank Bodendorf, Philipp Merkl, Joerg Franke
Summary: This paper reviews intelligent cost estimation methods for parts to be procured in the manufacturing industry through text mining, revealing the advantages of Artificial Neural Networks and Support Vector Machines in cost estimation, as well as the contribution of dimensionality reduction methods in reducing input parameters for cost estimation. It also points out the lack of methods supporting multi-level cost estimation and intelligent cost analysis result interpretation in the literature.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Review
Clinical Neurology
Minhui Zhong, Han Zhang, Chan Yu, Jinxia Jiang, Xia Duan
Summary: This study synthesized and evaluated the quality of studies on the application of machine learning techniques in predicting postpartum depression (PPD) risk. The researchers found that many models had a high risk of bias and applied ML techniques were yet to be deployed in clinical environments. More attention needs to be focused on model validation, improvement, and innovation.
JOURNAL OF AFFECTIVE DISORDERS
(2022)
Article
Psychology, Clinical
Ymkje Anna de Vries, Robert A. Schoevers, Julian P. T. Higgins, Marcus R. Munafo, Jojanneke A. Bastiaansen
Summary: Statistical power is generally low in trials of psychotherapy, pharmacotherapy, and complementary and alternative medicine for mood, anxiety, and psychotic disorders. Underpowered studies tend to produce larger effect sizes, indicating the presence of reporting bias. Increasing sample sizes and reducing bias are necessary to improve the reliability of published literature in this field.
PSYCHOLOGICAL MEDICINE
(2023)
Review
Public, Environmental & Occupational Health
Francesca Spiga, Mark Gibson, Sarah Dawson, Kate Tilling, George Davey Smith, Marcus R. Munafo, Julian P. T. Higgins
Summary: This study conducted a systematic review of tools designed for assessing risk of bias and/or quality of evidence in Mendelian randomization (MR) studies. The review identified seven tools specifically designed for assessing bias and quality of evidence in MR studies, all of which addressed the core assumptions of instrumental variable analysis.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2022)
Article
Medicine, General & Internal
Carole Lunny, Areti Angeliki Veroniki, Brian Hutton, Ian White, Jpt Higgins, James M. Wright, Ji Yoon Kim, Sai Surabi Thirugnanasampanthar, Shazia Siddiqui, Jennifer Watt, Lorenzo Moja, Nichole Taske, Robert C. Lorenz, Savannah Gerrish, Sharon Straus, Virginia Minogue, Franklin Hu, Kevin Lin, Ayah Kapani, Samin Nagi, Lillian Chen, Mona Akbar-nejad, Andrea C. Tricco
Summary: This study aimed to develop a risk of bias (RoB) tool for assessing network meta-analysis (NMA) and gather opinions from knowledge users. The Delphi process and knowledge user survey identified the content of the RoB NMA tool and revealed a preference for assessing both individual NMA results and authors' conclusions.
BMJ EVIDENCE-BASED MEDICINE
(2023)
Article
Public, Environmental & Occupational Health
Louise A. C. Millard, Alba Fernandez-Sanles, Alice R. Carter, Rachael A. Hughes, Kate Tilling, Tim P. Morris, Daniel Major-Smith, Gareth J. Griffith, Gemma L. Clayton, Emily Kawabata, George Davey Smith, Deborah A. Lawlor, Maria Carolina Borges
Summary: This study investigates potential selection bias in COVID-19 infection and prognosis studies due to non-random selection of analytic subsamples. The study finds that a broad range of characteristics is related to selection, with higher BMI being associated with increased odds of COVID-19 infection and death. The study also identifies significant bias in many simulated scenarios.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2022)
Article
Medicine, General & Internal
Ella Flemyng, Theresa Helen Moore, Isabelle Boutron, Julian P. T. Higgins, Asbjorn Hrobjartsson, Camilla Hansen Nejstgaard, Kerry Dwan
Summary: A systematic review evaluates and combines all the empirical evidence from studies that meet specific criteria to answer a research question, assessing the risk of bias in the included studies to enhance confidence in the conclusions. Cochrane Reviews have used a risk of bias tool since 2008, and a new version, RoB 2, was introduced in 2019 to improve usability and reflect current understanding of bias. This paper discusses lessons learned from the phased implementation of RoB 2 and provides tips for systematic reviewers.
BMJ EVIDENCE-BASED MEDICINE
(2023)
Article
Public, Environmental & Occupational Health
Charlotte E. Rutter, Louise A. C. Millard, Maria Carolina Borges, Deborah A. Lawlor
Summary: This study aimed to assess random measurement error in UK Biobank for all continuous variables and explore approaches to mitigate its impact on exposure-outcome associations. The results showed that random measurement error varies widely and is often non-negligible. The researchers provided relevant statistics and adaptable code to assist other researchers in exploring and correcting this issue.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2023)
Article
Health Care Sciences & Services
Louise A. C. Millard, Laura Johnson, Samuel R. Neaves, Peter A. Flach, Kate Tilling, Deborah A. Lawlor
Summary: This study aimed to demonstrate the feasibility of using Alexa to collect self-reported information in epidemiological research and to investigate participant acceptability. The results showed that although there were some issues with interacting with Alexa, participants were mostly willing to use voice-controlled systems in future research.
JMIR MHEALTH AND UHEALTH
(2023)
Article
Mathematical & Computational Biology
Rebecca M. Turner, Tim Band, Tim P. Morris, David J. Fisher, Julian P. T. Higgins, James R. Carpenter, Ian R. White
Summary: In this study, new local and global tests for inconsistency in network meta-analysis were proposed and applied to three example networks. The models were designed to handle treatments symmetrically and locate inconsistency in loops rather than in nodes or treatment comparisons. The global model showed potential for increased power compared to existing approaches.
STATISTICS IN MEDICINE
(2023)
Review
Medicine, General & Internal
Shuo Feng, Julie McLellan, Nicola Pidduck, Nia Roberts, Julian P. T. Higgins, Yoon Choi, Alane Izu, Mark Jit, Shabir A. Madhi, Kim Mulholland, Andrew J. Pollard, Beth Temple, Merryn Voysey
Summary: This systematic review and meta-analysis found differences in immunogenicity and efficacy between pneumococcal conjugate vaccines (PCV13 and PCV10). PCV13 demonstrated higher immunogenicity for specific serotypes and lower risk of seroinfection compared to PCV10. Additionally, a higher antibody response after vaccination was associated with a decreased risk of subsequent infection.
Review
Oncology
Lily J. Andrews, Zak A. Thornton, Ruqiya Saleh, Sarah Dawson, Susan C. Short, Richard Daly, Julian P. T. Higgins, Philippa Davies, Kathreena M. Kurian
Summary: This systematic review provides the first description of the genomic landscape of brain metastases derived from NSCLC, outlining frequently mutated genes and missense mutations that could have clinical significance. The study also highlights differences in genomic landscapes between ever versus never smokers and primary NSCLC compared to brain metastases, which could have implications for targeted drug selection and development.
NEURO-ONCOLOGY ADVANCES
(2023)
Review
Multidisciplinary Sciences
Aikaterini Vafeiadou, Michael J. Banissy, Jasmine F. M. Banissy, Julian P. T. Higgins, Guy Howard
Summary: This study conducted a scoping review to examine the impact of climate change on mental health in the Western Pacific Region (WPR). The findings showed that each country and sub-region in WPR has its own specific challenges and vulnerable populations related to climate change, highlighting the need for tailored approaches to mental health care. The most commonly reported mental health outcomes in response to climate-related challenges were the decline in mental well-being and the increase in post-traumatic stress disorder symptoms.
Meeting Abstract
Genetics & Heredity
Panagiota Pagoni, Julian P. T. Higgins, Deborah A. Lawlor, Evie Stergiakouli, Nicole M. Warrington, Kate Tilling, Tim Morris
GENETIC EPIDEMIOLOGY
(2022)
Article
Health Care Sciences & Services
Maria Pufulete, Kalaivani Mahadevan, Thomas W. Johnson, Christalla Pithara, Sabi Redwood, Umberto Benedetto, Julian P. T. Higgins, Barnaby C. Reeves
Summary: This study systematically identified potential confounders and co-interventions for three nonrandomized studies of interventions aiming to quantify bleeding in populations exposed to different dual antiplatelet therapy. The majority of factors were identified through a review, while interviews revealed hard-to-measure factors such as patient adherence and local prescribing culture. These methods could be widely applied in designing or reviewing nonrandomized studies of interventions.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2022)
Review
Medicine, General & Internal
Alexandra McAleenan, Hayley E. Jones, Ashleigh Kernohan, Tomos Robinson, Lena Schmidt, Sarah Dawson, Claire Kelly, Emmelyn Spencer Leal, Claire L. Faulkner, Abigail Palmer, Christopher Wragg, Sarah Jefferies, Sebastian Brandner, Luke Vale, Julian P. T. Higgins, Kathreena M. Kurian
Summary: Complete deletion of both the short arm of chromosome 1 (1p) and the long arm of chromosome 19 (19q), known as 1p/19q codeletion, is a mutation that can occur in gliomas. It is important for the diagnosis, prognosis, and treatment of gliomas. Fluorescent in situ hybridisation (FISH) and polymerase chain reaction (PCR)-based loss of heterozygosity (LOH) assays are the main tests used to detect 1p/19q codeletion. Other DNA-based techniques, such as single nucleotide polymorphism (SNP) array and next-generation sequencing (NGS), also show promise. The sensitivity and specificity of these tests vary, and further research is needed to determine their cost-effectiveness.
COCHRANE DATABASE OF SYSTEMATIC REVIEWS
(2022)
Article
Oncology
Pierre Blanchard, Anne W. M. Lee, Alexandra Carmel, Ng Wai Tong, Jun Ma, Anthony T. C. Chan, Ruey Long Hong, Ming-Yuan Chen, Lei Chen, Wen-Fei Li, Pei-Yu Huang, Dora L. W. Kwong, Sharon S. X. Poh, Roger Ngan, Hai-Qiang Mai, Camille Ollivier, George Fountzilas, Li Zhang, Jean Bourhis, Anne Auperin, Benjamin Lacas, Jean-Pierre Pignon
Summary: This study provides an update on the meta-analysis of chemotherapy in the treatment of nasopharyngeal carcinoma. The results confirm the benefits of concomitant chemotherapy and concomitant + adjuvant chemotherapy, and suggest that the addition of induction or adjuvant chemotherapy to concomitant chemotherapy improves tumor control and survival. The effectiveness of chemotherapy decreases with increasing patient age.
CLINICAL AND TRANSLATIONAL RADIATION ONCOLOGY
(2022)