Machine Learning For Text Classification Research Articles

Domain knowledge-powered attention for air traffic management hazardous events classification

The automated classification of hazardous events in Air Traffic Management (ATM) involves concise texts with specialized terminology. The problem is currently addressed by machine learning text classification methods; however, some methods overlook domain knowledge, while others require it excessively. This research aims to identify a process for integrating low-cost, text-based domain knowledge into classification to address the issue of domain shift. To achieve this, the Wide and Deep Bidirectional Encoder Representations from Transformers (WD-BERT) model is proposed, featuring a unique knowledge-powered attention mechanism. WD-BERT's Wide Attention module assesses the compatibility between input text and domain knowledge to determine class probabilities, while its Deep Attention module extracts contextual features guided by domain knowledge. Additionally, a text mining method is employed to extract domain knowledge from ATM regulation texts. The model is trained and evaluated using a dataset derived from the China ATM Hazard Source Database. It achieves a multi-label classification accuracy of 80.24% and an F1-micro score of 0.88, outperforming comparative models with state-of-the-art performance. Breakdown analyses of the model indicate that the carefully designed attention mechanism endows WD-BERT with the ability to integrate domain knowledge, allowing it to excel in contexts involving complex sentences, multiple terms, and domain shifts. The innovation of this study lies in the proposed domain knowledge-powered attention mechanism, which allows simply organized domain knowledge to effectively guide ATM hazardous events classification, alleviating the impact of domain shift. This method can also be applied to other vertical domains without knowledge graphs.

Negative Economic Sentiment Index Based on Finnish News Titles

We construct an index for measuring negative economic sentiment in Finland by using news titles collected from the Finnish broadcasting company Yle's archive. Our approach uses supervised machine learning text classification for detecting news titles featuring negative economic sentiment, and the monthly aggregated proportional frequencies of those titles are then used for defining the index. We find a negative correlation between our index and the consumer confidence index by Statistics Finland, and more remarkably, our index seems to lead the consumer confidence index, somewhat, by one month. We also show that our index correlates positively with Finnish stock market volatility. In addition, based on a simple VAR model, we examine how certain macro variables respond to changes in economic sentiment and show that our index could prove helpful in assessing the current and near-future state of the Finnish economy.

SENTIMENT LABELING AND TEXT CLASSIFICATION MACHINE LEARNING FOR WHATSAPP GROUP

The use of WhatsApp Group (WAG) for communication is increasing nowadays. WAG communication data can be analyzed from various perspectives. However, this data is imported in the form of unstructured text files. The aim of this research is to explore the potential use of the SentiwordNet lexicon for labeling the positive, negative, or neutral sentiment of WAG data from "Alumni94" and training and testing it with machine learning text classification models. The training and testing were conducted on six models, namely Random Forest, Decision Tree, Logistic Regression, K-Nearest Neighbors (KNN), Linear Support Vector Machine (SVM), and Artificial Neural Network. The labeling results indicate that neutral sentiment is the majority with 7588 samples, followed by 324 negative and 1617 positive samples. Among all the models, Random Forest showed better precision and recall, i.e., 83% and 64%. On the other hand, Decision Tree had slightly lower precision and recall, i.e., 80% and 66%, but exhibited a better f-measure of 71%. The accuracy evaluation results of the Random Forest and Decision Tree models showed significant performance compared to others, achieving an accuracy of 89% in classifying new messages. This research demonstrates the potential use of the SentiwordNet lexicon and machine learning in sentiment analysis of WAG data using the Random Forest and Decision Tree models

Using automated analysis to assess middle school students' competence with scientific argumentation

AbstractArgumentation is fundamental to science education, both as a prominent feature of scientific reasoning and as an effective mode of learning—a perspective reflected in contemporary frameworks and standards. The successful implementation of argumentation in school science, however, requires a paradigm shift in science assessment from the measurement of knowledge and understanding to the measurement of performance and knowledge in use. Performance tasks requiring argumentation must capture the many ways students can construct and evaluate arguments in science, yet such tasks are both expensive and resource‐intensive to score. In this study we explore how machine learning text classification techniques can be applied to develop efficient, valid, and accurate constructed‐response measures of students' competency with written scientific argumentation that are aligned with a validated argumentation learning progression. Data come from 933 middle school students in the San Francisco Bay Area and are based on three sets of argumentation items in three different science contexts. The findings demonstrate that we have been able to develop computer scoring models that can achieve substantial to almost perfect agreement between human‐assigned and computer‐predicted scores. Model performance was slightly weaker for harder items targeting higher levels of the learning progression, largely due to the linguistic complexity of these responses and the sparsity of higher‐level responses in the training data set. Comparing the efficacy of different scoring approaches revealed that breaking down students' arguments into multiple components (e.g., the presence of an accurate claim or providing sufficient evidence), developing computer models for each component, and combining scores from these analytic components into a holistic score produced better results than holistic scoring approaches. However, this analytical approach was found to be differentially biased when scoring responses from English learners (EL) students as compared to responses from non‐EL students on some items. Differences in the severity between human and computer scores for EL between these approaches are explored, and potential sources of bias in automated scoring are discussed.

Twenty Years of Machine-Learning-Based Text Classification: A Systematic Review

Machine-learning-based text classification is one of the leading research areas and has a wide range of applications, which include spam detection, hate speech identification, reviews, rating summarization, sentiment analysis, and topic modelling. Widely used machine-learning-based research differs in terms of the datasets, training methods, performance evaluation, and comparison methods used. In this paper, we surveyed 224 papers published between 2003 and 2022 that employed machine learning for text classification. The Preferred Reporting Items for Systematic Reviews (PRISMA) statement is used as the guidelines for the systematic review process. The comprehensive differences in the literature are analyzed in terms of six aspects: datasets, machine learning models, best accuracy, performance evaluation metrics, training and testing splitting methods, and comparisons among machine learning models. Furthermore, we highlight the limitations and research gaps in the literature. Although the research works included in the survey perform well in terms of text classification, improvement is required in many areas. We believe that this survey paper will be useful for researchers in the field of text classification.

Implementation of Machine Learning for Text Classification Using the Naive Bayes Algorithm in Academic Information Systems at Sebelas Maret University Indonesia

This study implements machine learning using the Naive Bayes algorithm to create a text classification in an engineering professional program information system. The methods used include text data collection, preprocessing, feature extraction, Naive Bayes model training, and evaluation using data testing. This study made a classification model to predict text categories with a test accuracy rate of 0.975 and a training accuracy of 0.967. This research contributes to the development of text classification in information systems and can be used as a basis for further study.

Interpretable machine learning text classification for clinical computed tomography reports – a case study of temporal bone fracture

BackgroundMachine learning (ML) has demonstrated success in classifying patients’ diagnostic outcomes in free-text clinical notes. However, due to the machine learning model's complexity, interpreting the mechanism behind classification results remains difficult. MethodsWe investigated interpretable representations of text-based machine learning classification models. We created machine learning models to classify temporal bone fractures based on 164 temporal bone computed tomography (CT) text reports. We adopted the XGBoost, Support Vector Machine, Logistic Regression, and Random Forest algorithms. To interpret models, we used two major methodologies: (1) We calculated the average word frequency score (WFS) for keywords. The word frequency score shows the frequency gap between positively and negatively classified cases. (2) We used Local Interpretable Model-Agnostic Explanations (LIME) to show the word-level contribution to bone fracture classification. ResultsIn temporal bone fracture classification, the random forest model achieved an average F1-score of 0.93. WFS revealed a difference in keyword usage between fracture and non-fracture cases. Additionally, LIME visualized the keywords' contributions to the classification results. The evaluation of LIME-based interpretation achieved the highest interpreting accuracy of 0.97. ConclusionThe interpretable text explainer can improve physicians' understanding of machine learning predictions. By providing simple visualization, our model can increase the trust of computerized models. Our model supports more transparent computerized decision-making in clinical settings.

Greasing the wheels for comparative communication research: Supervised text classification for multilingual corpora

Employing supervised machine learning for text classification is already a resource-intensive endeavor in a monolingual setting. However, facing the challenge to classify a multilingual corpus, the cost of producing the required annotated documents quickly exceeds even generous time and financial constraints. We show how tools like automated annotation and machine translation can not only efficiently but also effectively be employed for the classification of a multilingual corpus with supervised machine learning. Our findings demonstrate that good results can already be achieved with the machine translation of about 250 to 350 documents per category class and language and a dictionary in just one language, which we perceive as a realistic scenario for many projects. The methodological strategy is applied to study migration frames in seven languages (news discourse in seven European countries) and discussed and evaluated for its usability in comparative communication research.

Global Trends in Cancer Nanotechnology: A Qualitative Scientific Mapping Using Content-Based and Bibliometric Features for Machine Learning Text Classification.

Simple SummaryThis study is a new way of providing potential opportunities for prevention, diagnosis, and therapy to investigate the comprehensive trends in cancer nanotechnology research. This paper applied the qualitative method of bibliometric analysis on cancer nanotechnology using the PubMed database during the years 2000–2021. It mined nearly 50,000 papers published in multiple reputed journals. The impact of our findings is significant, which focuses on hybrid medical models and content-based and bibliometric features for machine learning models in cancer detection, diagnosis, imaging, and therapy related to cancer nanotechnology in the world. We mainly identified and classified the top and significant keywords, countries, authors, affiliations, and research areas representing the documents in the top 100 journals in cancer nanotechnology, which will help researchers explore more powerful anticancer nanomedicines in the next five to ten years.This study presents a new way to investigate comprehensive trends in cancer nanotechnology research in different countries, institutions, and journals providing critical insights to prevention, diagnosis, and therapy. This paper applied the qualitative method of bibliometric analysis on cancer nanotechnology using the PubMed database during the years 2000–2021. Inspired by hybrid medical models and content-based and bibliometric features for machine learning models, our results show cancer nanotechnology studies have expanded exponentially since 2010. The highest production of articles in cancer nanotechnology is mainly from US institutions, with several countries, notably the USA, China, the UK, India, and Iran as concentrated focal points as centers of cancer nanotechnology research, especially in the last five years. The analysis shows the greatest overlap between nanotechnology and DNA, RNA, iron oxide or mesoporous silica, breast cancer, and cancer diagnosis and cancer treatment. Moreover, more than 50% of the information related to the keywords, authors, institutions, journals, and countries are considerably investigated in the form of publications from the top 100 journals. This study has the potential to provide past and current lines of research that can unmask comprehensive trends in cancer nanotechnology, key research topics, or the most productive countries and authors in the field.

Machine Learning Based Embedded Code Multi-Label Classification

With the development of Internet of Things (IoT) technology, embedded based electronic devices have penetrated every corner of our daily lives. As the brain of IoT devices, embedded based micro controller unit (MCU) plays an irreplaceable role. The functions of the MCUs are becoming more and more powerful and complicated, which brings huge challenges to embedded programmers. Embedded code, which is highly related to the hardware resources, differs from other popular programming code. The hardware configuration may be a big challenge to the programmers, who may only be good at software development and algorithm design. Online code searching can be time consuming and cannot guarantee an optimal approach. To solve this problem, in this paper, an embedded code classifier, which is designed to help embedded programmers to search for the most efficient code with precise tags, is demonstrated. A high quality embedded code dataset is built. A tag correlated multi-label machine learning model is developed for the embedded code dataset. The experimental results show that the proposed code dataset structure is proved to be more efficient on embedded code classification. The proposed embedded classifier algorithm shows a promising result on embedded code dataset. And it outperforms the traditional machine learning text classification models.

Computationally Analyzing Social Media Text for Topics: A Primer for Advertising Researchers

Advertising researchers and practitioners are increasingly using social media analytics (SMA), but focused overviews that explain how to use various SMA techniques are scarce. We focus on how researchers and practitioners can computationally analyze topics of conversation in social media posts, compare each to a human-coded topic analysis of a brand’s Twitter feed, and provide recommendations on how to assess and choose which computational methods to use. The computational methodologies that we survey in this article are text preprocessed summarization, phrase mining, topic modeling, supervised machine learning for text classification, and semantic topic tagging.

An Optimized E-Lecture Video Retrieval based on Machine Learning Classification

The advent of internet has lead to colossal development of e-learning frameworks. The efficiency of such systems however relies on the effectiveness and fast content based retrieval approaches. This paper presents a methodology for efficient search and retrieval of lecture videos based on Machine Learning (ML) text classification algorithm. The text transcript is generated exclusively from the audio content extracted from the video lectures. This content is utilized for the summary and keyword extraction which is used for training the ML text classification model. An optimized search is achieved based on the trained ML model. The performance of the system is compared by training the system using Naive Bayes, Support Vector Machine and Logistic Regression algorithms. Performance evaluation was done by precision, recall, F-score and accuracy of the search for each of the classifiers. It is observed that the system trained on Naive Bayes classification algorithm achieved better performance both in terms of time and also with respect to relevancy of the search results.

Extracting Alcohol and Substance Abuse Status from Clinical Notes: The Added Value of Nursing Data.

We applied an open source natural language processing (NLP) system "NimbleMiner" to identify clinical notes with mentions of alcohol and substance abuse. NimbleMiner allows users to rapidly discover clinical vocabularies (using word embedding model) and then implement machine learning for text classification. We used a large inpatient dataset with over 50,000 intensive care unit admissions (MIMIC II). Clinical notes included physician-written discharge summaries (n = 51,201) and nursing notes (n = 412,343). We first used physician-written discharge summaries to train the system's algorithm and then added nursing notes to the physician-written discharge summaries and evaluated algorithms prediction accuracy. Adding nursing notes to the physician-written discharge summaries resulted in almost two-fold vocabulary expansion. NimbleMiner slightly outperformed other state-of-the-art NLP systems (average F-score = .84), while requiring significantly less time for the algorithms development.: Our findings underline the importance of nursing data for the analysis of electronic patient records.

An effective Decision Support System for social media listening based on cross-source sentiment analysis models

Nowadays, companies and enterprises are more and more incline to exploit the pervasive action of on-line social media, such as Facebook, Twitter and Instagram. Indeed, several promotional and marketing campaigns are carried out by concurrently adopting several social medial channels. These campaigns reach very quickly a wide range of different categories of users, since many people spend most of their time on on-line social media during the day.In this work, a Decision Support System (DSS) is presented, which is able to efficiently support companies and enterprises in managing promotional and marketing campaigns on multiple social media channels. The proposed DSS continuously monitors multiple social channels, by collecting social media users’ comments on promotions, products, and services. Then, through the analysis of these data, the DSS estimates the reputation of brands related to specific companies and provides feedbacks about a digital marketing campaign.The core of the proposed DSS is a Sentiment Analysis Engine (SAE), which is able to estimate the users’ sentiment in terms of positive, negative or neutral polarity, expressed in a comment. The SAE is based on a machine learning text classification model, which is initially trained by using real data streams coming from different social media platforms specialized in user reviews (e.g., TripAdvisor). Then, the monitoring and the sentiment classification are carried out on the comments continuously extracted from a set of public pages and channels of publicly available social networking platforms (e.g., Facebook, Twitter, and Instagram). This approach is labeled as cross-source sentiment analysis.After some discussions on the design and the implementation of the proposed DSS, some results are shown about the experimentation of the proposed DSS on two scenarios, namely restaurants and consumer electronics online shops. Specifically, first the application of effective sentiment analysis models, created relying on user reviews is discussed: the models achieve accuracies higher than 90%. Then, such models are embedded into the proposed DSS. Finally, the results of a social listening campaign are presented. The campaign was carried out by fusing data streams coming from real social channels of popular companies belonging to the selected scenarios.

Discussions of Alcohol Use in an Online Social Network for Smoking Cessation: Analysis of Topics, Sentiment, and Social Network Centrality.

Few Internet smoking cessation programs specifically address the impact of alcohol use during a quit attempt, despite its common role in relapse. This study used topic modeling to describe the most prevalent topics about alcohol in an online smoking cessation community, the prevalence of negative sentiment expressed about alcohol use in the context of a quit attempt (i.e., alcohol should be limited or avoided during a quit attempt) within topics, and the degree to which topics differed by user social connectivity within the network. Data were analyzed from posts from the online community of a larger Internet cessation program, spanning January 1, 2012 to May 31, 2015 and included records of 814,258 online posts. Posts containing alcohol-related content (n=7,199) were coded via supervised machine learning text classification to determine whether the post expressed negative sentiment about drinking in the context of a quit attempt. Correlated topic modeling (CTM) was used to identify a set of 10 topics of at least 1% prevalence based on the frequency of word occurrences among alcohol-related posts; the distribution of negative sentiment and user social network connectivity was examined across the most salient topics. Three salient topics (with prevalence ≥10%) emerged from the CTM, with distinct themes of (i) cravings and temptations; (ii) parallel between nicotine addiction and alcoholism; and (iii) celebratory discussions of quit milestones including "virtual" alcohol use and toasts. Most topics skewed toward nonnegative sentiment about alcohol. The prevalence of each topic differed by users' social connectivity in the network. Future work should examine whether outcomes in Internet interventions are improved by tailoring social network content to match user characteristics, topics, and network behavior.

Anticipating acceptance of emerging technologies using twitter: the case of self-driving cars

In an early stage of developing emerging technologies, there is often great uncertainty regarding their future success. Companies can reduce this uncertainty by listening to the voice of customers as the customer eventually decides to accept an emerging technology or not. We show that risk and benefit perceptions are central determinants of acceptance of emerging technologies. We present an analysis of risk and benefit perception of self-driving cars from March 2015 until October 2016. In this period, we analyzed 1,963,905 tweets using supervised machine learning for text classification. Furthermore, we developed two new metrics, risk rate (RR) and benefit rate (BR), which allow analyzing risk and benefit perceptions on social media quantitatively. With our results, we provide impetus for further research on acceptance of self-driving cars and a methodological contribution to acceptance of emerging technologies research. Furthermore, we identify crucial issues in the public perception of self-driving cars and provide guidance for the management of emerging technologies to increase the likelihood of their acceptance.

Predicting High Imaging Utilization Based on Initial Radiology Reports:: A Feasibility Study of Machine Learning

Imaging utilization has significantly increased over the last two decades, and is only recently showing signs of moderating. To help healthcare providers identify patients at risk for high imaging utilization, we developed a prediction model to recognize high imaging utilizers based on their initial imaging reports. The prediction model uses a machine learning text classification framework. In this study, we used radiology reports from 18,384 patients with at least one abdomen computed tomography study in their imaging record at Stanford Health Care as the training set. We modeled the radiology reports in a vector space and trained a support vector machine classifier for this prediction task. We evaluated our model on a separate test set of 4791 patients. In addition to high prediction accuracy, in our method, we aimed at achieving high specificity to identify patients at high risk for high imaging utilization. Our results (accuracy: 94.0%, sensitivity: 74.4%, specificity: 97.9%, positive predictive value: 87.3%, negative predictive value: 95.1%) show that a prediction model can enable healthcare providers to identify in advance patients who are likely to be high utilizers of imaging services. Machine learning classifiers developed from narrative radiology reports are feasible methods to predict imaging utilization. Such systems can be used to identify high utilizers, inform future image ordering behavior, and encourage judicious use of imaging.

Features and machine learning classification of connected speech samples from patients with autopsy proven Alzheimer's disease with and without additional vascular pathology.

Mixed vascular and Alzheimer-type dementia and pure Alzheimer's disease are both associated with changes in spoken language. These changes have, however, seldom been subjected to systematic comparison. In the present study, we analyzed language samples obtained during the course of a longitudinal clinical study from patients in whom one or other pathology was verified at post mortem. The aims of the study were twofold: first, to confirm the presence of differences in language produced by members of the two groups using quantitative methods of evaluation; and secondly to ascertain the most informative sources of variation between the groups. We adopted a computational approach to evaluate digitized transcripts of connected speech along a range of language-related dimensions. We then used machine learning text classification to assign the samples to one of the two pathological groups on the basis of these features. The classifiers' accuracies were tested using simple lexical features, syntactic features, and more complex statistical and information theory characteristics. Maximum accuracy was achieved when word occurrences and frequencies alone were used. Features based on syntactic and lexical complexity yielded lower discrimination scores, but all combinations of features showed significantly better performance than a baseline condition in which every transcript was assigned randomly to one of the two classes. The classification results illustrate the word content specific differences in the spoken language of the two groups. In addition, those with mixed pathology were found to exhibit a marked reduction in lexical variation and complexity compared to their pure AD counterparts.

Novel Text Categorization by Amalgamation of Augmented K-Nearest Neighbourhoodclassification and K-Medoids Clustering

Machine learning for text classification is the underpinning of document cataloging, news filtering, document steering and exemplification. In text mining realm, effective feature selection is significant to make the learning task more accurate and competent. One of the traditional lazy text classifier k-Nearest Neighborhood (kNN) has a major pitfall in calculating the similarity between all the objects in training and testing sets, there by leads to exaggeration of both computational complexity of the algorithm and massive consumption of main memory. To diminish these shortcomings in viewpoint of a data-mining practitioner an amalgamative technique is proposed in this paper using a novel restructured version of kNN called AugmentedkNN(AkNN) and k-Medoids(kMdd) clustering.The proposed work comprises preprocesses on the initial training set by imposing attribute feature selection for reduction of high dimensionality, also it detects and excludes the high-fliers samples in the initial training set and restructures a constrictedtraining set. The kMdd clustering algorithm generates the cluster centers (as interior objects) for each category and restructures the constricted training set with centroids. This technique is amalgamated with AkNNclassifier that was prearranged with text mining similarity measures. Eventually, significantweights and ranks were assigned to each object in the new training set based upon their accessory towards the object in testing set. Experiments conducted on Reuters-21578 a UCI benchmark text mining data set, and comparisons with traditional kNNclassifier designates the referredmethod yieldspreeminentrecitalin both clustering and classification.

An extensive empirical study of feature selection metrics for text classification

Machine learning for text classification is the cornerstone of document categorization, news filtering, document routing, and personalization. In text domains, effective feature selection is essent...