Avoid common mistakes on your manuscript.
This special issue of the International Journal of Data Science and Analytics includes the DSAA 2023 Journal Track papers, which cover advances in both theoretical and practical aspects of data science and analytics, with a particular focus on trustworthy data science and analytics. The track contains nine papers, all of which underwent rigorous review by the guest editors and invited reviewers.
The paper by Cooper Doe, Vladimir Knezevic, Maya Zeng, Francesca Spezzano, and Liljana Babinkostova, titled “Modeling the Time to Share Fake and Real News in Online Social Networks”, addresses the problem of predicting the time it takes to share real or fake news on social media platforms. The authors model this problem as a survival analysis task, and a statistical method is proposed used to predict the time until a specific event occurs.
The paper by Mohamed El-Moussaoui, Mohamed Hanine, Ali Kartit, and Tarik Agouti, titled “A Multi-Agent-Based Approach for Community Detection Using Association Rules”, presents a novel community detection approach that shifts the focus from traditional topological properties to the topical properties of nodes and edges.
Ridesharing is becoming increasingly important in urban transportation. In their paper titled “Contrastive Text Summarization: A Survey”, Thomas Ströhle, Ricardo Campos, and Adam Jatowt provide a systematic literature review on comparative summarization, highlighting various methods, datasets, metrics, and applications.
The paper titled “FLICs (Facebook Language Informal Corpus): A Novel Dataset for Informal Language” introduces a dataset specifically designed for modelling informal language. Francis Rakotomalala, Aimé Richard Hajalalaina, Manda Vy Ravonimanantsoa Ndaohialy, Anselme Andriavelonera Alexandre, and Andriatina H. Ranaivoson aim to address the lack of linguistic diversity in existing datasets by providing over 800,000 informal texts, facilitating a deeper understanding of contemporary linguistic trends in informal communication.
The paper by Dinh Pham-Toan and Tai Vo-Van, titled “Building the Classification Model Based on the Genetic Algorithm and the Improved Bayesian Method”, introduces a classification model that incorporates significant enhancements through the Bayesian method and genetic algorithm (BGA). This model offers the capability to classify multiple elements simultaneously, unlike existing algorithms that typically handle only one element at a time.
The paper by Jurgen van den Hoogen, Dan Hudson, Stefan Bloemheuvel, and Martin Atzmueller, titled “Hyperparameter Analysis of Wide-Kernel CNN Architectures in Industrial Fault Detection: An Exploratory Study”, investigates the impact of various architectural hyperparameters on the performance of one-dimensional convolutional neural networks (CNNs) on industrial fault detection. Using a multi-method approach, the paper specifically focuses on wide-kernel CNN models for industrial fault detection, which have shown strong performance in tasks such as classifying vibration signals from sensors.
The paper by Rohan Raut and Francesca Spezzano, titled “Enhancing Hate Speech Detection with User Characteristics”, proposes combining tweet textual features with a variety of user features to improve state-of-the-art hate speech detection techniques. The user features include demographic information, behavioural patterns, network-based data, emotions, personality traits, readability, and writing style.
The paper by Sai Ram Aditya Parisineni and Mayukha Pal, titled “Enhancing Trust and Interpretability of Complex Machine Learning Models Using Local Interpretable Model Agnostic SHAP Explanations”, integrates Shapley values within the LIME framework. This work advances the field of machine learning model interpretability and offers a practical solution to address the challenges posed by complex and opaque ML models.
The world is facing significant challenges related to climate change and the management of natural disasters. The paper by Shivam Chauhan, Ajay Singh Jethoo, Ajay Mishra, and Vaibhav Varshney, titled “Duo Satellite-Based Remotely Sensed Land Surface Temperature Prediction By Various Methods of Machine Learning”, focuses on predicting land surface temperatures in the smart city of Ajmer, India, using duo satellite-based remote sensing data from 2003 to 2021. The study employs various machine learning techniques to predict both same-day and future-day temperatures.
These nine papers represent quite different directions in the fast-growing area of data science and analytics. We hope that these papers will inspire more research in this exciting area.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, B., Zhu, F. & Wei, W. Editorial: DSAA 2023 journal track on theoretical and practical data science and analytics. Int J Data Sci Anal 18, 351–352 (2024). https://doi.org/10.1007/s41060-024-00645-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41060-024-00645-3