A novel grid-based many-objective swarm intelligence approach for sentiment analysis in social media

Predicting patients' sentiments about medications using artificial intelligence techniques

The increasing development of technology has led to the increase of digital data in various fields, such as medication-related texts. Sentiment Analysis (SA) in medication is essential to give clinicians insights into patients' feedback about the treatment procedure. Therefore, this study intends to develop Artificial Intelligence (AI) models to predict patients' sentiments. This study used a large medication review dataset to perform a SA of medications. Three scenarios were considered for classification, including two, three, and ten classes. The Word2Vec algorithm and pre-trained word embeddings, including the general and clinical domains, were utilized in model development. Seven Machine Learning (ML) and Deep Learning (DL) models were developed for various scenarios. The best hyperparameters for all models were fine-tuned. Moreover, two ensemble learning models were developed from the proposed ML and DL models. For the first time, a technique was implemented to interpret the results for explainability and interpretability. The results showed that the developed deep ensemble model (DL_ENS), using PubMed and PMC, as pre-trained word embedding representation, achieved the best results, with accuracy and F1-Score of 92.96% and 92.27% in two classes, 92.18% and 88.50 in three classes, and 90.31% and 67.07% in ten classes, respectively. Combining DL models and developing a DL_ENS with clinical domain pre-trained word embedding representation can accurately predict classes and scores of patients' sentiments about medications compared to previous studies on the same dataset. Due to the transparency in decision-making, our DL_ENS model can be used as an auxiliary tool to help clinicians prescribe medications.

Modelling and evaluation of mechanical performance and environmental impacts of sustainable concretes using a multi-objective optimization based innovative interpretable artificial intelligence method

This study focuses on modelling sustainable concretes' mechanical and environmental properties with interpretable artificial intelligence-based automated rule extraction, management of waste materials, and meeting future prospects. In this context, 24 sustainable concrete series containing fly ash and recycled aggregates were produced. Compressive strength tests were performed on these specimens at 7, 28, and 90 days, and their mechanical properties were evaluated. Concrete classes (Class A, B, C, D) were determined using the compressive strength values obtained for each test day. The results of each concrete class were analyzed using a unique interpretable multi-objective rule extraction model, and the range values of the materials used were determined. The applied multi-objective rule extraction method is used for the first time in the literature, and its most important novelty is that, unlike other black-box artificial intelligence methods, it can also enable the creation of sustainable concrete recipes. After the range values of the materials used were found by automatic rule extraction, environmental impact assessments were performed. Among the impact categories, energy consumption and global warming potential were considered. The energy consumption results for Rule 4 were calculated as 814.8-1467.1 MJ, respectively, and a reduction of approximately 44.5% was observed. Similarly, global warming potentials for Rule 3 were obtained as 187.0-267.3 kg m3, respectively, with a reduction of about 30%. The limitations and future prospects of the study have been extensively investigated. The importance of adopting explainable/interpretable artificial intelligence-based approaches within the scope of sustainable development and circular economy goals to develop social infrastructure and buildings with low carbon emissions that are feasible in terms of mechanical and environmental properties is highlighted. Multi-Objective Optimization Based Innovative Interpretable Artificial Intelligence Method, used for the first time in mechanical and environmental modelling of sustainable concretes, can make significant contributions to the literature and future studies.

Increasing the explainability and success in classification: many-objective classification rule mining based on chaos integrated SPEA2

Classification rule mining represents a significant field of machine learning, facilitating informed decision-making through the extraction of meaningful rules from complex data. Many classification methods cannot simultaneously optimize both explainability and different performance metrics at the same time. Metaheuristic optimization-based solutions, inspired by natural phenomena, offer a potential paradigm shift in this field, enabling the development of interpretable and scalable classifiers. In contrast to classical methods, such rule extraction-based solutions are capable of classification by taking multiple purposes into consideration simultaneously. To the best of our knowledge, although there are limited studies on metaheuristic based classification, there is not any method that optimize more than three objectives while increasing the explainability and interpretability for classification task. In this study, data sets are treated as the search space and metaheuristics as the many-objective rule discovery strategy and study proposes a metaheuristic many-objective optimization-based rule extraction approach for the first time in the literature. Chaos theory is also integrated to the optimization method for performance increment and the proposed chaotic rule-based SPEA2 algorithm enables the simultaneous optimization of four different success metrics and automatic rule extraction. Another distinctive feature of the proposed algorithm is that, in contrast to classical random search methods, it can mitigate issues such as correlation and poor uniformity between candidate solutions through the use of a chaotic random search mechanism in the exploration and exploitation phases. The efficacy of the proposed method is evaluated using three distinct data sets, and its performance is demonstrated in comparison with other classical machine learning results.

An Enhanced IDBO-CNN-BiLSTM Model for Sentiment Analysis of Natural Disaster Tweets

The Internet's development has prompted social media to become an essential channel for disseminating disaster-related information. Increasing the accuracy of emotional polarity recognition in tweets is conducive to the government or rescue organizations understanding the public's demands and responding appropriately. Existing sentiment analysis models have some limitations of applicability. Therefore, this research proposes an IDBO-CNN-BiLSTM model combining the swarm intelligence optimization algorithm and deep learning methods. First, the Dung Beetle Optimization (DBO) algorithm is improved by adopting the Latin hypercube sampling, integrating the Osprey Optimization Algorithm (OOA), and introducing an adaptive Gaussian-Cauchy mixture mutation disturbance. The improved DBO (IDBO) algorithm is then utilized to optimize the Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) model's hyperparameters. Finally, the IDBO-CNN-BiLSTM model is constructed to classify the emotional tendencies of tweets associated with the Hurricane Harvey event. The empirical analysis indicates that the proposed model achieves an accuracy of 0.8033, outperforming other single and hybrid models. In contrast with the GWO, WOA, and DBO algorithms, the accuracy is enhanced by 2.89%, 2.82%, and 2.72%, respectively. This study proves that the IDBO-CNN-BiLSTM model can be applied to assist emergency decision-making in natural disasters.

Enhancing tertiary students' programming skills with an explainable Educational Data Mining approach

Educational Data Mining (EDM) holds promise in uncovering insights from educational data to predict and enhance students' performance. This paper presents an advanced EDM system tailored for classifying and improving tertiary students' programming skills. Our approach emphasizes effective feature engineering, appropriate classification techniques, and the integration of Explainable Artificial Intelligence (XAI) to elucidate model decisions. Through rigorous experimentation, including an ablation study and evaluation of six machine learning algorithms, we introduce a novel ensemble method, Stacking-SRDA, which outperforms others in accuracy, precision, recall, f1-score, ROC curve, and McNemar test. Leveraging XAI tools, we provide insights into model interpretability. Additionally, we propose a system for identifying skill gaps in programming among weaker students, offering tailored recommendations for skill enhancement.

An Adaptive Spiral Strategy Dung Beetle Optimization Algorithm: Research and Applications

The Dung Beetle Optimization (DBO) algorithm, a well-established swarm intelligence technique, has shown considerable promise in solving complex engineering design challenges. However, it is hampered by limitations such as suboptimal population initialization, sluggish search speeds, and restricted global exploration capabilities. To overcome these shortcomings, we propose an enhanced version termed Adaptive Spiral Strategy Dung Beetle Optimization (ADBO). Key enhancements include the application of the Gaussian Chaos strategy for a more effective population initialization, the integration of the Whale Spiral Search Strategy inspired by the Whale Optimization Algorithm, and the introduction of an adaptive weight factor to improve search efficiency and enhance global exploration capabilities. These improvements collectively elevate the performance of the DBO algorithm, significantly enhancing its ability to address intricate real-world problems. We evaluate the ADBO algorithm against a suite of benchmark algorithms using the CEC2017 test functions, demonstrating its superiority. Furthermore, we validate its effectiveness through applications in diverse engineering domains such as robot manipulator design, triangular linkage problems, and unmanned aerial vehicle (UAV) path planning, highlighting its impact on improving UAV safety and energy efficiency.

A blockchain-based evaluation approach to analyse customer satisfaction using AI techniques

Due to technological advancements and consumer demands, online shopping creates new features and adapts to new standards. A robust customer satisfaction prediction model concerning trust and privacy platforms can encourage an organization to make better decisions about its service and quality. This study presented an approach to predict consumer satisfaction using the blockchain-based framework combining the Multi-Dimensional Naive Bayes-K Nearest Neighbor (MDNB-KNN) and the Multi-Objective Logistic Particle Swarm Optimization Algorithm (MOL-PSOA). A regression model is employed to quantify the impact of various production factors on customer satisfaction. The proposed method yields better levels of measurement for customer satisfaction (98%), accuracy (95%), necessary time (60%), precision (95%), and recall (95%) compared to existing studies. Measuring consumer satisfaction with a trustworthy platform facilitates to development of the conceptual and practical distinctions influencing customers' purchasing decisions.

A novel hybrid multi-thread metaheuristic approach for fake news detection in social media

In fake news detection, intelligent optimization seems to be a more effective and explainable solution methodology than the black-box methods that have been extensively used in the literature. This study takes the optimization-based method one step further and proposes a novel, multi-thread hybrid metaheuristic approach for fake news detection in social media. The most innovative feature of the proposed method is that it uses a supervisor thread mechanism, which simultaneously monitors and improves the performance and search patterns of metaheuristic algorithms running parallel. With the supervisor thread mechanism, it is possible to analyse different key attribute combinations in the search space. In addition, this study develops a software framework that allows this model to be implemented easily. It tests the performance of the proposed model on three different data sets, respectively containing news about Covid-19, the Syrian War, and daily politics. The proposed method is evaluated in comparison to the results of fifteen different well-known deep models and classification algorithms. Experimental results prove the success of the proposed model and that it can produce competitive results.