User Classification on Online Social Networks by Post Frequency

This paper proposes a technique for classifying user accounts on social networks to detect fraud in Online Social Networks (OSN). The main purpose of our classification is to recognize the patterns of users from Human, Bots or Cyborgs. Classic and consolidated approaches of Text Mining employ textual features from Natural Language Processing (NLP) for classification, but some drawbacks as computational cost, the huge amount of data could rise in real-life scenarios. This work uses an approach based on statistical frequency parameters of the user posting to distinguish the types of users without textual content. We perform the experiment over a Twitter dataset and as learn-based algorithms in classification task we compared Random Forest (RF), Support Vector Machine (SVM), k-nearest Neighbors (k-NN), Gradient Boosting Machine (GBM) and Extreme Gradient Boosting (XGBoost). Using the standard parameters of each algorithm, we achieved accuracy results of 88% and 84% by RF and XGBoost, respectively

Download Full-text

Classification of Individual Finger Movements from Right Hand Using fNIRS Signals

Sensors ◽

10.3390/s21237943 ◽

2021 ◽

Vol 21 (23) ◽

pp. 7943

Author(s):

Haroon Khan ◽

Farzan M. Noori ◽

Anis Yazidi ◽

Md Zia Uddin ◽

M. N. Afzal Khan ◽

...

Keyword(s):

Nearest Neighbors ◽

Machine Learning Algorithms ◽

Finger Tapping ◽

Gradient Boosting ◽

Support Vector ◽

K Nearest Neighbors ◽

Physiological Noise ◽

Individual Finger ◽

Extreme Gradient Boosting ◽

Depth Analysis

Functional near-infrared spectroscopy (fNIRS) is a comparatively new noninvasive, portable, and easy-to-use brain imaging modality. However, complicated dexterous tasks such as individual finger-tapping, particularly using one hand, have been not investigated using fNIRS technology. Twenty-four healthy volunteers participated in the individual finger-tapping experiment. Data were acquired from the motor cortex using sixteen sources and sixteen detectors. In this preliminary study, we applied standard fNIRS data processing pipeline, i.e. optical densities conversation, signal processing, feature extraction, and classification algorithm implementation. Physiological and non-physiological noise is removed using 4th order band-pass Butter-worth and 3rd order Savitzky–Golay filters. Eight spatial statistical features were selected: signal-mean, peak, minimum, Skewness, Kurtosis, variance, median, and peak-to-peak form data of oxygenated haemoglobin changes. Sophisticated machine learning algorithms were applied, such as support vector machine (SVM), random forests (RF), decision trees (DT), AdaBoost, quadratic discriminant analysis (QDA), Artificial neural networks (ANN), k-nearest neighbors (kNN), and extreme gradient boosting (XGBoost). The average classification accuracies achieved were 0.75±0.04, 0.75±0.05, and 0.77±0.06 using k-nearest neighbors (kNN), Random forest (RF) and XGBoost, respectively. KNN, RF and XGBoost classifiers performed exceptionally well on such a high-class problem. The results need to be further investigated. In the future, a more in-depth analysis of the signal in both temporal and spatial domains will be conducted to investigate the underlying facts. The accuracies achieved are promising results and could open up a new research direction leading to enrichment of control commands generation for fNIRS-based brain-computer interface applications.

Download Full-text

Explainable Artificial Intelligence for Sarcasm Detection in Dialogues

Wireless Communications and Mobile Computing ◽

10.1155/2021/2939334 ◽

2021 ◽

Vol 2021 ◽

pp. 1-13

Author(s):

Akshi Kumar ◽

Shubham Dikshit ◽

Victor Hugo C. Albuquerque

Keyword(s):

Language Processing ◽

Learning Algorithm ◽

Real Life ◽

Decision Makers ◽

Gradient Boosting ◽

Trained Classifier ◽

Extreme Gradient Boosting ◽

Interpretable Model ◽

The Right ◽

Post Hoc

Sarcasm detection in dialogues has been gaining popularity among natural language processing (NLP) researchers with the increased use of conversational threads on social media. Capturing the knowledge of the domain of discourse, context propagation during the course of dialogue, and situational context and tone of the speaker are some important features to train the machine learning models for detecting sarcasm in real time. As situational comedies vibrantly represent human mannerism and behaviour in everyday real-life situations, this research demonstrates the use of an ensemble supervised learning algorithm to detect sarcasm in the benchmark dialogue dataset, MUStARD. The punch-line utterance and its associated context are taken as features to train the eXtreme Gradient Boosting (XGBoost) method. The primary goal is to predict sarcasm in each utterance of the speaker using the chronological nature of a scene. Further, it is vital to prevent model bias and help decision makers understand how to use the models in the right way. Therefore, as a twin goal of this research, we make the learning model used for conversational sarcasm detection interpretable. This is done using two post hoc interpretability approaches, Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP), to generate explanations for the output of a trained classifier. The classification results clearly depict the importance of capturing the intersentence context to detect sarcasm in conversational threads. The interpretability methods show the words (features) that influence the decision of the model the most and help the user understand how the model is making the decision for detecting sarcasm in dialogues.

Download Full-text

Machine Learning Models for COVID-19 Detection in Brazil Based on Symptoms (Preprint)

10.2196/preprints.27293 ◽

2021 ◽

Author(s):

Íris Viana dos Santos Santana ◽

Andressa C. M. da Silveira ◽

Álvaro Sobrinho ◽

Lenardo Chaves e Silva ◽

Leandro Dias da Silva ◽

...

Keyword(s):

Machine Learning ◽

Early Stage ◽

Area Under The Curve ◽

Supervised Machine Learning ◽

Gradient Boosting ◽

Support Vector ◽

Accuracy Score ◽

K Nearest Neighbors ◽

Runny Nose ◽

Extreme Gradient Boosting

BACKGROUND controlling the COVID-19 outbreak in Brazil is considered a challenge of continental proportions due to the high population and urban density, weak implementation and maintenance of social distancing strategies, and limited testing capabilities. OBJECTIVE to contribute to addressing such a challenge, we present the implementation and evaluation of supervised Machine Learning (ML) models to assist the COVID-19 detection in Brazil based on early-stage symptoms. METHODS firstly, we conducted data preprocessing and applied the Chi-squared test in a Brazilian dataset, mainly composed of early-stage symptoms, to perform statistical analyses. Afterward, we implemented ML models using the Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), Decision Tree (DT), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost) algorithms. We evaluated the ML models using precision, accuracy score, recall, the area under the curve, and the Friedman and Nemenyi tests. Based on the comparison, we grouped the top five ML models and measured feature importance. RESULTS the MLP model presented the highest mean accuracy score, with more than 97.85%, when compared to GBM (> 97.39%), RF (> 97.36%), DT (> 97.07%), XGBoost (> 97.06%), KNN (> 95.14%), and SVM (> 94.27%). Based on the statistical comparison, we grouped MLP, GBM, DT, RF, and XGBoost, as the top five ML models, because the evaluation results are statistically indistinguishable. The ML models` importance of features used during predictions varies from gender, profession, fever, sore throat, dyspnea, olfactory disorder, cough, runny nose, taste disorder, and headache. CONCLUSIONS supervised ML models effectively assist the decision making in medical diagnosis and public administration (e.g., testing strategies), based on early-stage symptoms that do not require advanced and expensive exams.

Download Full-text

Sentiment Analysis using Optimized Feature Sets in Different Facebook/Twitter Dataset Domains using Big Data

Iraqi Journal for Computer Science and Mathematics ◽

10.52866/ijcsm.2022.01.01.007 ◽

2022 ◽

pp. 64-70

Author(s):

Mohammed Ibrahim Al-mashhadani ◽

Kilan M. Hussein ◽

Enas Tariq Khudir ◽

Muhammad ilyas

Keyword(s):

Data Mining ◽

Big Data ◽

Sentiment Analysis ◽

Language Processing ◽

Online Social Networks ◽

Opinion Mining ◽

Real Life ◽

Online Reviews ◽

Support Vector ◽

Main Task

Now days, in many real life applications, the sentiment analysis plays very vital role for automatic prediction of human being activities especially on online social networks (OSNs). Therefore since from last decade, the research on opinion mining and sentiment analysis is growing with increasing volume of online reviews available over the social media networks like Facebook OSNs. Sentiment analysis falls under the data mining domain research problem. Sentiment analysis is kind of text mining process used to determine the subjective attitude like sentiment from the written texts and hence becoming the main research interest in domain of natural language processing and data mining. The main task in sentiment analysis is classifying human sentiment with objective of classifying the sentiment or emotion of end users for their specific text on OSNs. There are number of research methods designed already for sentiment analysis. There are many factors like accuracy, efficiency, speed etc. used to evaluate the effectiveness of sentiment analysis methods. The MapReduce framework under the domain of big-data is used to minimize the speed of execution and efficiency recently with many data mining methods. The sentiment analysis for Facebook OSNs messages is very challenging tasks as compared to other sentiment analysis because of misspellings and slang words presence in twitter dataset. In this paper, different solutions recently presented are discussed in detail. Then proposed the new approach for sentiment analysis based on hybrid features extraction methods and multi-class Support Vector Machine (SVM). These algorithms are designed using the Big-data techniques to optimize the performance of sentiment analysis

Download Full-text

A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph17218187 ◽

2020 ◽

Vol 17 (21) ◽

pp. 8187

Author(s):

Joshua Cohen ◽

Jennifer Wright-Berryman ◽

Lesley Rohlfs ◽

Donald Wright ◽

Marci Campbell ◽

...

Keyword(s):

Machine Learning ◽

Language Processing ◽

Suicide Risk ◽

External Validation ◽

Risk Identification ◽

Gradient Boosting ◽

Support Vector ◽

Extreme Gradient Boosting ◽

Adolescent Therapy ◽

Therapy Sessions

Background: As adolescent suicide rates continue to rise, innovation in risk identification is warranted. Machine learning can identify suicidal individuals based on their language samples. This feasibility pilot was conducted to explore this technology’s use in adolescent therapy sessions and assess machine learning model performance. Method: Natural language processing machine learning models to identify level of suicide risk using a smartphone app were tested in outpatient therapy sessions. Data collection included language samples, depression and suicidality standardized scale scores, and therapist impression of the client’s mental state. Previously developed models were used to predict suicidal risk. Results: 267 interviews were collected from 60 students in eight schools by ten therapists, with 29 students indicating suicide or self-harm risk. During external validation, models were trained on suicidal speech samples collected from two separate studies. We found that support vector machines (AUC: 0.75; 95% CI: 0.69–0.81) and logistic regression (AUC: 0.76; 95% CI: 0.70–0.82) lead to good discriminative ability, with an extreme gradient boosting model performing the best (AUC: 0.78; 95% CI: 0.72–0.84). Conclusion: Voice collection technology and associated procedures can be integrated into mental health therapists’ workflow. Collected language samples could be classified with good discrimination using machine learning methods.

Download Full-text

Comparative Study of Several Machine Learning Algorithms for Classification of Unifloral Honeys

Foods ◽

10.3390/foods10071543 ◽

2021 ◽

Vol 10 (7) ◽

pp. 1543

Author(s):

Fernando Mateo ◽

Andrea Tarazona ◽

Eva María Mateo

Keyword(s):

Machine Learning ◽

Discriminant Analysis ◽

Pollen Grains ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

K Nearest Neighbors ◽

Test Set ◽

Extreme Gradient Boosting ◽

Classical Methodology

Unifloral honeys are highly demanded by honey consumers, especially in Europe. To ensure that a honey belongs to a very appreciated botanical class, the classical methodology is palynological analysis to identify and count pollen grains. Highly trained personnel are needed to perform this task, which complicates the characterization of honey botanical origins. Organoleptic assessment of honey by expert personnel helps to confirm such classification. In this study, the ability of different machine learning (ML) algorithms to correctly classify seven types of Spanish honeys of single botanical origins (rosemary, citrus, lavender, sunflower, eucalyptus, heather and forest honeydew) was investigated comparatively. The botanical origin of the samples was ascertained by pollen analysis complemented with organoleptic assessment. Physicochemical parameters such as electrical conductivity, pH, water content, carbohydrates and color of unifloral honeys were used to build the dataset. The following ML algorithms were tested: penalized discriminant analysis (PDA), shrinkage discriminant analysis (SDA), high-dimensional discriminant analysis (HDDA), nearest shrunken centroids (PAM), partial least squares (PLS), C5.0 tree, extremely randomized trees (ET), weighted k-nearest neighbors (KKNN), artificial neural networks (ANN), random forest (RF), support vector machine (SVM) with linear and radial kernels and extreme gradient boosting trees (XGBoost). The ML models were optimized by repeated 10-fold cross-validation primarily on the basis of log loss or accuracy metrics, and their performance was compared on a test set in order to select the best predicting model. Built models using PDA produced the best results in terms of overall accuracy on the test set. ANN, ET, RF and XGBoost models also provided good results, while SVM proved to be the worst.

Download Full-text

Language-Independent Fake News Detection: English, Portuguese, and Spanish Mutual Features

Future Internet ◽

10.3390/fi12050087 ◽

2020 ◽

Vol 12 (5) ◽

pp. 87 ◽

Cited By ~ 1

Author(s):

Hugo Queiroz Abonizio ◽

Janaina Ignacio de Morais ◽

Gabriel Marques Tavares ◽

Sylvio Barbon Junior

Keyword(s):

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Detection Accuracy ◽

Fake News ◽

K Nearest Neighbors ◽

Detection Model ◽

Online Social Media ◽

Extreme Gradient Boosting ◽

Independent Features

Online Social Media (OSM) have been substantially transforming the process of spreading news, improving its speed, and reducing barriers toward reaching out to a broad audience. However, OSM are very limited in providing mechanisms to check the credibility of news propagated through their structure. The majority of studies on automatic fake news detection are restricted to English documents, with few works evaluating other languages, and none comparing language-independent characteristics. Moreover, the spreading of deceptive news tends to be a worldwide problem; therefore, this work evaluates textual features that are not tied to a specific language when describing textual data for detecting news. Corpora of news written in American English, Brazilian Portuguese, and Spanish were explored to study complexity, stylometric, and psychological text features. The extracted features support the detection of fake, legitimate, and satirical news. We compared four machine learning algorithms (k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGB)) to induce the detection model. Results show our proposed language-independent features are successful in describing fake, satirical, and legitimate news across three different languages, with an average detection accuracy of 85.3% with RF.

Download Full-text

Modelling on Car-Sharing Serial Prediction Based on Machine Learning and Deep Learning

Complexity ◽

10.1155/2022/8843000 ◽

2022 ◽

Vol 2022 ◽

pp. 1-20

Author(s):

Nihad Brahimi ◽

Huaping Zhang ◽

Lin Dai ◽

Jianzi Zhang

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Research Work ◽

Gradient Boosting ◽

Support Vector ◽

Learning Models ◽

Car Sharing ◽

K Nearest Neighbors ◽

Extreme Gradient Boosting ◽

On The Road

The car-sharing system is a popular rental model for cars in shared use. It has become particularly attractive due to its flexibility; that is, the car can be rented and returned anywhere within one of the authorized parking slots. The main objective of this research work is to predict the car usage in parking stations and to investigate the factors that help to improve the prediction. Thus, new strategies can be designed to make more cars on the road and fewer in the parking stations. To achieve that, various machine learning models, namely vector autoregression (VAR), support vector regression (SVR), eXtreme gradient boosting (XGBoost), k-nearest neighbors (kNN), and deep learning models specifically long short-time memory (LSTM), gated recurrent unit (GRU), convolutional neural network (CNN), CNN-LSTM, and multilayer perceptron (MLP), were performed on different kinds of features. These features include the past usage levels, Chongqing’s environmental conditions, and temporal information. After comparing the obtained results using different metrics, we found that CNN-LSTM outperformed other methods to predict the future car usage. Meanwhile, the model using all the different feature categories results in the most precise prediction than any of the models using one feature category at a time

Download Full-text

Question to Question Similarity Analysis Using Morphological, Syntactic, Semantic, and Lexical Features

JUCS - Journal of Universal Computer Science ◽

10.3897/jucs.2020.036 ◽

2020 ◽

Vol 26 (6) ◽

pp. 671-697

Author(s):

Mahmoud Hammad ◽

Mohammad Al-Smadi ◽

Qanita Baker ◽

Muntaha D ◽

Nour Al-Khdour ◽

...

Keyword(s):

Language Processing ◽

Text Processing ◽

Gradient Boosting ◽

Support Vector ◽

Arabic Text ◽

Feature Selection Technique ◽

Adaptive Boosting ◽

Machine Learning Classifiers ◽

Extreme Gradient Boosting ◽

Promising Solution

In the digitally connected world that we are living in, people expect to get answers to their questions spontaneously. This expectation increased the burden on Question/Answer platforms such as Stack Overflow and many others. A promising solution to this problem is to detect if a question being asked is similar to a question in the database, then present the answer of the detected question to the user. To address this challenge, we propose a novel Natural Language Processing (NLP) approach that detects if two Arabic questions are similar or not using their extracted morphological, syntactic, semantic, lexical, overlapping, and semantic lexical features. Our approach involves several phases including Arabic text processing, novel feature extraction, and text classifications. Moreover, we conducted a comparison between seven different machine learning classifiers. The included classifiers are: Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), Extreme Gradient Boosting (XGB), Random Forests (RF), Adaptive Boosting (AdaBoost), and Multilayer Perceptron (MLP). To conduct our experiments, we used a real-world questions dataset consisting of around 19,136 questions (9,568 pairs of questions) in which our approach achieved 82.93% accuracy using our XGB model on the best features selected by the Random Forest feature selection technique. This high accuracy of our model shows the ability of our approach to correctly detect similar Arabic questions and hence increases user satisfactions.

Download Full-text

Machine Learning Methods to Predict Social Media Disaster Rumor Refuters

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph16081452 ◽

2019 ◽

Vol 16 (8) ◽

pp. 1452 ◽

Cited By ~ 4

Author(s):

Shihang Wang ◽

Zongmin Li ◽

Yuhong Wang ◽

Qi Zhang

Keyword(s):

Machine Learning ◽

Language Processing ◽

Machine Learning Techniques ◽

Gradient Boosting ◽

Support Vector ◽

Short Text ◽

Learning Techniques ◽

Extreme Gradient Boosting ◽

Effective Decision Support ◽

Short Text Similarity

This research provides a general methodology for distinguishing disaster-related anti-rumor spreaders from a non-ignorant population base, with strong connections in their social circle. Several important influencing factors are examined and illustrated. User information from the most recent posted microblog content of 3793 Sina Weibo users was collected. Natural language processing (NLP) was used for the sentiment and short text similarity analyses, and four machine learning techniques, i.e., logistic regression (LR), support vector machines (SVM), random forest (RF), and extreme gradient boosting (XGBoost) were compared on different rumor refuting microblogs; after which a valid and robust distinguishing XGBoost model was trained and validated to predict who would retweet disaster-related rumor refuting microblogs. Compared with traditional prediction variables that only access user information, the similarity and sentiment analyses of the most recent user microblog contents were found to significantly improve prediction precision and robustness. The number of user microblogs also proved to be a valuable reference for all samples during the prediction process. This prediction methodology could be possibly more useful for WeChat or Facebook as these have relatively stable closed-loop communication channels, which means that rumors are more likely to be refuted by acquaintances. Therefore, the methodology is going to be further optimized and validated on WeChat-like channels in the future. The novel rumor refuting approach presented in this research harnessed NLP for the user microblog content analysis and then used the analysis results of NLP as additional prediction variables to identify the anti-rumor spreaders. Therefore, compared to previous studies, this study presents a new and effective decision support for rumor countermeasures.

Download Full-text