Search results

The authors constructed an automatic essay scoring (AES) model in a discussion forum where the result was compared with scores given by human evaluators. This research proposes essay scoring, which is conducted through two parameters, semantic and keyword similarities, using a SentenceTransformers pre-trained model that can construct the highest vector embedding. Combining these models is used to optimize the model with increasing accuracy.

The development of the model in the study is divided into seven stages: (1) data collection, (2) pre-processing data, (3) selected pre-trained SentenceTransformers model, (4) semantic similarity (sentence pair), (5) keyword similarity, (6) calculate final score and (7) evaluating model.

The multilingual paraphrase-multilingual-MiniLM-L12-v2 and distilbert-base-multilingual-cased-v1 models got the highest scores from comparisons of 11 pre-trained multilingual models of SentenceTransformers with Indonesian data (Dhini and Girsang, 2023). Both multilingual models were adopted in this study. A combination of two parameters is obtained by comparing the response of the keyword extraction responses with the rubric keywords. Based on the experimental results, proposing a combination can increase the evaluation results by 0.2.

This study uses discussion forum data from the general biology course in online learning at the open university for the 2020.2 and 2021.2 semesters. Forum discussion ratings are still manual. In this survey, the authors created a model that automatically calculates the value of discussion forums, which are essays based on the lecturer's answers moreover rubrics.

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

Purpose: Students’ transition from education to employment is influenced by factors like the length and calibre of their education, demography, labour market conditions, and the general state of the economy. Regardless of the economy, education systems should seek to ensure that students have the skills required for the labour market. This will help them better transition from school to work. This study examines the work skills that companies require for entry-level positions in Romania.

Need for Study: Previously, text analysis studies treated the job market only for the IT industry in Romania. To understand the demand-side opportunities and restrictions, assessing the employment opportunities for young people in the Romanian labour market is necessary.

Methodology: A text mining approach from 842 unstructured data of the existing job positions in October 2022 for fresh graduates or students is used in this chapter. The study uses data from LinkedIn job descriptions in the Romanian job market. The methodology involved is focused on text retrieval, text-pre-processing, word cloud analysis, network analysis, and topic modelling.

Findings: The empirical findings revealed that the most common words in job descriptions are experience, team, work, skills, development, knowledge, support, data, business, and software. The correlation network revealed that the most correlated pairs of words are gender–sexual–race–religion–origin–diversity–age–identity–orientation–colour–equal–marital.

Practical Implications: This study looked at the job market and used text analytics to extract a space of skill and qualification dimensions from job announcements relevant to the Romanian employment market instead of depending on subjective knowledge.

This study leverages social network analysis (SNA) to visualise the way students interacted with online resources and uses the data obtained from SNA as features for supervised machine learning algorithms to predict whether a student will successfully complete a course.

The exploration and visualisation of the data were first carried out to gain a better understanding of the students, the course(s) each student was enrolled in and each course’s virtual learning resources. Following this, the construction of the social network graphs was performed to depict how each student behaved online before the degree centralities were computed for each of the nodes in a social network graph. Data pre-processing to assign labels based on the final result a student obtained in a course was then performed before we trained and tested models to predict which students did or did not graduate.

The study’s findings demonstrate that the constructed predictive model has good performance, as shown by the accuracy, precision, recall and f-measure metrics. The outcomes also showed that students’ use of online resources is a crucial element that influences how well they perform in their academics.

The similarity index is as low as 9%.

The authors hope to filter valuable information from online reviews, obtain objective and accurate information about the demands of auto consumers and help auto companies develop more reasonable production and marketing strategies for healthy and sustainable development. This paper aims to discuss the aforementioned objectives.

The authors collected review data from online automotive forums and generated a corpus after pre-processing. Then, the authors extracted consumer demands and topics using the LDA model. Finally, the authors used a trained Word2vec tool to extend the consumer demand topics.

Different types of vehicle consumers have the same demands, such as “Space,” “Power Performance,” and “Brand Comparison,” and distinct demands, such as “Appearance,” “Safety,” “Service,” and “New Energy Features”; consumers who buy new energy vehicles are still accustomed to comparing with the brands or models of fuel vehicles; new energy vehicles consumers pay more attention to services and service quality during the purchasing and using process.

The development time of new energy vehicles is relatively short, with some models being available for only one year or even six months. The smaller amount of available data may impact the applicability of topic models. The sample size, especially for new energy vehicles, needs to be increased to improve the general applicability of topic models further.

First, this measure helps online review websites improve their existing review publication mechanisms, enhance the overall quality of online review content, increase user traffic and promote the healthy development of online review websites. Second, this allows for timely adjustments in future product production and sales plans and further enhances automotive companies' ability to leverage online reviews for Internet marketing.

The authors have improved the accuracy and stability of the fused topic model, providing a scientific and efficient research tool for multi-dimensional topic mining of online reviews. With the help of research results, consumers can more easily understand the discussion topics and thus filter out valuable reference information. As a result, automotive companies may gain information about consumer demands and product quality feedback and thus quickly adjust production and marketing strategies to increase sales and market share.

The hygroscopic properties of 3D-printed filaments and moisture absorption itself during the process result in dimensional inaccuracy, particularly for nozzle movement along the x-axis and for micro-scale features. In view of that, this study aims to analyze in depth the dimensional errors and deviations of the fused filament fabrication (FFF)/fused deposition modeling (FDM) 3D-printed micropillars (MPs) from the reference values. A detailed analysis into the variability in printed dimensions below 1 mm in width without any deformations in the printed shape of the designed features, for challenging filaments like polymethyl methacrylate (PMMA) has been done. The study also explores whether the printed shape retains the designed structure.

A reference model for MPs of width 800 µm and height 2,000 µm is selected to generate a g-code model after pre-processing of slicing and meshing parameters for 3D printing of micro-scale structure with defined boundaries. Three SETs, SET-A, SET-B and SET-C, for nozzle diameter of 0.2 mm, 0.25 mm and 0.3 mm, respectively, have been prepared. The SETs containing the MPs were fabricated with the spacing (S) of 2,000 µm, 3,200 µm and 4,000 µm along the print head x-axis. The MPs were measured by taking three consecutive measurements (top, bottom and middle) for the width and one for the height.

The prominent highlight of this study is the successful FFF/FDM 3D printing of thin features (<1mm) without any deformation. The mathematical analysis of the variance of the optical microscopy measurements concluded that printed dimensions for micropillar widths did not vary significantly, retaining more than 65% of the recording within the first standard deviation (SD) (±1 s). The minimum value of SD is obtained from the samples of SET-B, that is, 31.96 µm and 35.865 µm, for height and width, respectively. The %RE for SET-B samples is 5.09% for S = 2,000µm, 3.86% for S = 3,200µm and 1.09% for S = 4,000µm. The error percentage is so small that it could be easily compensated by redesigning.

The study does not cover other 3D printing techniques of additive manufacturing like stereolithography, digital light processing and material jetting.

The presented study can be potentially implemented for the rapid prototyping of microfluidics mixer, bioseparator and lab-on-chip devices, both for membrane-free bioseparation based on microfiltration, plasma extraction from whole blood, size-selection trapping of unwanted blood cells, and also for membrane-based plasma extraction that requires supporting microstructures. Our developed process may prove to be far more economical than the other existing techniques for such applications.

For the first time, this work presents a comprehensive analysis of the fabrication of micropillars using FDM/FFF 3D printing and PMMA in filament form. The primary focus of the study is to minimize the dimensional inaccuracies in the 3D printed devices containing thin features, especially in the area of biomedical engineering, by delivering benefits from the choice of the parameters. Thus, on the basis of errors and deviations, a thorough comparison of the three SETs of the fabricated micropillars has been done.

This study aims to develop a machine learning model to detect structure fire fatalities using a dataset comprising 11,341 cases from 2011 to 2019.

Exploratory data analysis (EDA) was conducted prior to modelling, in which ten machine learning models were experimented with.

The main fatal structure fire risk factors were fires originating from bedrooms, living areas and the cooking/dining areas. The highest fatality rate (20.69%) was reported for fires ignited due to bedding (23.43%), despite a low fire incident rate (3.50%). Using 21 structure fire features, Random Forest (RF) yielded the best detection performance with 86% accuracy, followed by Decision Tree (DT) with bagging (accuracy = 84.7%).

Limitations of the study are pertaining to data quality and grouping of categories in the data pre-processing stage, which could affect the performance of the models.

The study is the first of its kind to manipulate risk factors to detect fatal structure classification, particularly focussing on structure fire fatalities. Most of the previous studies examined the importance of fire risk factors and their relationship to the fire risk level.

Lubricating oil leakage is a common issue in thermal power plant operation sites, requiring prompt equipment maintenance. The real-time detection of leakage occurrences could avoid disruptive consequences caused by the lack of timely maintenance. Currently, inspection operations are mostly carried out manually, resulting in time-consuming processes prone to health and safety hazards. To overcome such issues, this paper proposes a machine vision-based inspection system aimed at automating the oil leakage detection for improving the maintenance procedures.

The approach aims at developing a novel modular-structured automatic inspection system. The image acquisition module collects digital images along a predefined inspection path using a dual-light (i.e. ultraviolet and blue light) illumination system, deploying the fluorescence of the lubricating oil while suppressing unwanted background noise. The image processing module is designed to detect the oil leakage within the digital images minimizing detection errors. A case study is reported to validate the industrial suitability of the proposed inspection system.

On-site experimental results demonstrate the capabilities to complete the automatic inspection procedures of the tested industrial equipment by achieving an oil leakage detection accuracy up to 99.13%.

The proposed inspection system can be adopted in industrial context to detect lubricant leakage ensuring the equipment and the operators safety.

The proposed inspection system adopts a computer vision approach, which deploys the combination of two separate sources of light, to boost the detection capabilities, enabling the application for a variety of particularly hard-to-inspect industrial contexts.

This paper aims to develop predictive methods, based on recurrent neural networks, useful to support facility managers in building maintenance tasks, by collecting information coming from a computerized maintenance management system (CMMS).

This study applies data-driven and text-mining approaches to a CMMS data set comprising more than 14,500 end-users’ requests for corrective maintenance actions, collected over 14 months. Unidirectional long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM) recurrent neural networks are trained to predict the priority of each maintenance request and the related technical staff assignment. The data set is also used to depict an overview of corrective maintenance needs and related performances and to verify the most relevant elements in the building and how the current facility management (FM) relates to the requests.

The study shows that LSTM and Bi-LSTM recurrent neural networks can properly recognize the words contained in the requests, thus correctly and automatically assigning the priority and predicting the technical staff to assign for each end-user’s maintenance request. The obtained global accuracy is very high, reaching 93.3% for priority identification and 96.7% for technical staff assignment. Results also show the main critical building elements for maintenance requests and the related intervention timings.

This work shows that LSTM and Bi-LSTM recurrent neural networks can automate the assignment process of end-users’ maintenance requests if trained with historical CMMS data. Results are promising; however, the trained LSTM and Bi-LSTM RNN can be applied only to different hospitals adopting similar categorization.

The data-driven and text-mining approaches can be integrated into the CMMS to support corrective maintenance management by facilities management contractors, i.e. to properly and timely identify the actions to be carried out and the technical staff to assign.

The improvement of the maintenance of the health-care system is a key component of improving health service delivery. This work shows how to reduce health-care service interruptions due to maintenance needs through machine learning methods.

This study develops original methods and tools easily integrable into IT workflow systems (i.e. CMMS) in the FM field.

The purpose of this study is to develop a domain independent, cost-effective, time-saving and semi-automated ontology generation framework that could extract taxonomic concepts from unstructured text corpus. In the human disease domain, ontologies are found to be extremely useful for managing the diversity of technical expressions in favour of information retrieval objectives. The boundaries of these domains are expanding so fast that it is essential to continuously develop new ontologies or upgrade available ones.

This paper proposes a semi-automated approach that extracts entities/relations via text mining of scientific publications. Text mining-based ontology (TmbOnt)-named code is generated to assist a user in capturing, processing and establishing ontology elements. This code takes a pile of unstructured text files as input and projects them into high-valued entities or relations as output. As a semi-automated approach, a user supervises the process, filters meaningful predecessor/successor phrases and finalizes the demanded ontology-taxonomy. To verify the practical capabilities of the scheme, a case study was performed to drive glaucoma ontology-taxonomy. For this purpose, text files containing 10,000 records were collected from PubMed.

The proposed approach processed over 3.8 million tokenized terms of those records and yielded the resultant glaucoma ontology-taxonomy. Compared with two famous disease ontologies, TmbOnt-driven taxonomy demonstrated a 60%–100% coverage ratio against famous medical thesauruses and ontology taxonomies, such as Human Disease Ontology, Medical Subject Headings and National Cancer Institute Thesaurus, with an average of 70% additional terms recommended for ontology development.

According to the literature, the proposed scheme demonstrated novel capability in expanding the ontology-taxonomy structure with a semi-automated text mining approach, aiming for future fully-automated approaches.