Pandiaraj A., Sundar C. and Pavalarajan S.
Up to date development in sentiment analysis has resulted in a symbolic growth in the volume of study, especially on more subjective text types, namely, product or movie reviews…
Abstract
Purpose
Up to date development in sentiment analysis has resulted in a symbolic growth in the volume of study, especially on more subjective text types, namely, product or movie reviews. The key difference between these texts with news articles is that their target is defined and unique across the text. Hence, the reviews on newspaper articles can deal with three subtasks: correctly spotting the target, splitting the good and bad content from the reviews on the concerned target and evaluating different opinions provided in a detailed manner. On defining these tasks, this paper aims to implement a new sentiment analysis model for article reviews from the newspaper.
Design/methodology/approach
Here, tweets from various newspaper articles are taken and the sentiment analysis process is done with pre-processing, semantic word extraction, feature extraction and classification. Initially, the pre-processing phase is performed, in which different steps such as stop word removal, stemming, blank space removal are carried out and it results in producing the keywords that speak about positive, negative or neutral. Further, semantic words (similar) are extracted from the available dictionary by matching the keywords. Next, the feature extraction is done for the extracted keywords and semantic words using holoentropy to attain information statistics, which results in the attainment of maximum related information. Here, two categories of holoentropy features are extracted: joint holoentropy and cross holoentropy. These extracted features of entire keywords are finally subjected to a hybrid classifier, which merges the beneficial concepts of neural network (NN), and deep belief network (DBN). For improving the performance of sentiment classification, modification is done by inducing the idea of a modified rider optimization algorithm (ROA), so-called new steering updated ROA (NSU-ROA) into NN and DBN for weight update. Hence, the average of both improved classifiers will provide the classified sentiment as positive, negative or neutral from the reviews of newspaper articles effectively.
Findings
Three data sets were considered for experimentation. The results have shown that the developed NSU-ROA + DBN + NN attained high accuracy, which was 2.6% superior to particle swarm optimization, 3% superior to FireFly, 3.8% superior to grey wolf optimization, 5.5% superior to whale optimization algorithm and 3.2% superior to ROA-based DBN + NN from data set 1. The classification analysis has shown that the accuracy of the proposed NSU − DBN + NN was 3.4% enhanced than DBN + NN, 25% enhanced than DBN and 28.5% enhanced than NN and 32.3% enhanced than support vector machine from data set 2. Thus, the effective performance of the proposed NSU − ROA + DBN + NN on sentiment analysis of newspaper articles has been proved.
Originality/value
This paper adopts the latest optimization algorithm called the NSU-ROA to effectively recognize the sentiments of the newspapers with NN and DBN. This is the first work that uses NSU-ROA-based optimization for accurate identification of sentiments from newspaper articles.
Details
Keywords
Md Shamim Hossain, Humaira Begum, Md. Abdur Rouf and Md. Mehedul Islam Sabuj
The goal of the current research is to use different machine learning (ML) approaches to examine and predict customer reviews of food delivery apps (FDAs).
Abstract
Purpose
The goal of the current research is to use different machine learning (ML) approaches to examine and predict customer reviews of food delivery apps (FDAs).
Design/methodology/approach
Using Google Play Scraper, data from five food delivery service providers were collected from the Google Play store. Following cleaning the reviews, the filtered texts were classified as having negative, positive, or neutral sentiments, which were then scored using two unsupervised sentiment algorithms (AFINN and Valence Aware Dictionary for sentiment Reasoning (VADER)). Furthermore, the authors employed four ML approaches to categorize each review of FDAs into the respective sentiment class.
Findings
According to the study's findings, the majority of customer reviews of FDAs were positive. This research also revealed that, while all of the methods (decision tree, linear support vector machine, random forest classifier and logistic regression) can appropriately classify the reviews into a sentiment category, support vector machines (SVM) beats the others in terms of model accuracy. The authors' study also showed that logistic regression provided the highest recall, F1 score and lowest Root Mean Square Error (RMSE) among the four ML models.
Practical implications
The findings aid FDAs in determining customer review behavior. The study's findings could help food apps developers better understand how customers feel about the developers' products and services. The food apps developer can learn how to use ML techniques to better understand the users' behavior.
Originality/value
The current study uses ML methodologies to investigate and predict consumer attitude regarding FDAs.
Details
Keywords
Md Shamim Hossain, Mst Farjana Rahman, Md Kutub Uddin and Md Kamal Hossain
There is a strong prerequisite for organizations to analyze customer review behavior to evaluate the competitive business environment. The purpose of this study is to analyze and…
Abstract
Purpose
There is a strong prerequisite for organizations to analyze customer review behavior to evaluate the competitive business environment. The purpose of this study is to analyze and predict customer reviews of halal restaurants using machine learning (ML) approaches.
Design/methodology/approach
The authors collected customer review data from the Yelp website. The authors filtered the reviews of only halal restaurants from the original data set. Following cleaning, the filtered review texts were classified as positive, neutral or negative sentiments, and those sentiments were scored using the AFINN and VADER sentiment algorithms. Also, the current study applies four machine learning methods to classify each review toward halal restaurants into its sentiment class.
Findings
The experiment showed that most of the customer reviews toward halal restaurants were positive. The authors also discovered that all of the methods (decision tree, linear support vector machine, logistic regression and random forest classifier) can correctly classify the review text into sentiment class, but logistic regression outperforms the others in terms of accuracy.
Practical implications
The results facilitate halal restaurateurs in identifying customer review behavior.
Social implications
Sentiment and emotions, according to appraisal theory, form the basis for all interactions, facilitating cognitive functions and supporting prospective customers in making sense of experiences. Emotion theory also describes human affective states that determine motives and actions. The study looks at how potential customers might react to a halal restaurant’s consensus on social media based on reviewers’ opinions of halal restaurants because emotions can be conveyed through reviews.
Originality/value
This study applies machine learning approaches to analyze and predict customer sentiment based on the review texts toward halal restaurants.
Details
Keywords
Jagdeep Singh, Harwinder Singh and Gurpreet Singh
The purpose of this paper is to uncover the significance of lean manufacturing technique in manufacturing environments.
Abstract
Purpose
The purpose of this paper is to uncover the significance of lean manufacturing technique in manufacturing environments.
Design/methodology/approach
Lean manufacturing is a management approach focused on incremental improvements in operations. Different lean strategies are being utilized by manufacturing industry to improve the performance of current manufacturing system processes. This study attempts to evaluate the performance of different lean manufacturing tools in the manufacturing industry of northern India. The importance level of different lean tools, important benefits achieved after successful implementation of lean manufacturing approach and benefits occurred after implementation of different lean tools have been identified. A questionnaire survey in the case company has been performed and the most important element of lean manufacturing has been implemented.
Findings
Results explicitly depict that just-in-time manufacturing is the most important element of lean manufacturing. Results indicate the net savings of rupees 242,208 annually after implementing lean manufacturing technique in a case company.
Originality/value
The paper demonstrates the practical application of lean technique showing how it can bring real breakthroughs in saving cost in the manufacturing industry.
Details
Keywords
Abdulrahman Al-Shami, Rami Joseph Oweis and Mohamed Ghazi Al-Fandi
This paper aims to report on the development of a novel electrochemical amperometric immunosensor to diagnose early hepatocellular carcinoma (HCC) by detecting the Midkine (MDK…
Abstract
Purpose
This paper aims to report on the development of a novel electrochemical amperometric immunosensor to diagnose early hepatocellular carcinoma (HCC) by detecting the Midkine (MDK) biomarker.
Design/methodology/approach
Anti-Midkine antibodies were immobilized covalently through carbodiimides chemistry on carbon screen-printed electrodes modified with carboxylated multi-walled carbon nanotubes. The development process was characterized using cyclic voltammetry, electrochemical impedimetric spectroscopy, Fourier transform infrared spectroscopy and atomic force microscopy. Differential pulse voltammetry was used to investigate the immunosensor performance in detecting MDK antigen within the concentration range of 1 pg/ml to 100 ng/ml.
Findings
MDK immunosensor exhibited high sensitivity and linearity with a detection limit of 0.8 pg/ml and a correlation coefficient of 0.99. The biosensor also demonstrated high selectivity, stability and reproducibility.
Originality/value
The developed MDK immunosensor could be a promising tool to diagnose HCC and reduce the number of related deaths.
Details
Keywords
Erhan Ada, Halil Kemal Ilter, Muhittin Sagnak and Yigit Kazancoglu
The main aim of this study is to understand the role of smart technologies and show the rankings of various smart technologies in collection and classification of electronic waste…
Abstract
Purpose
The main aim of this study is to understand the role of smart technologies and show the rankings of various smart technologies in collection and classification of electronic waste (e-waste).
Design/methodology/approach
This study presents a framework integrating the concepts of collection and classification mechanisms and smart technologies. The criteria set includes three main, which are economic, social and environmental criteria, including a total of 15 subcriteria. Smart technologies identified in this study were robotics, multiagent systems, autonomous tools, smart vehicles, data-driven technologies, Internet of things (IOT), cloud computing and big data analytics. The weights of all criteria were found using fuzzy analytic network process (ANP), and the scores of smart technologies which were useful for collection and classification of e-waste were calculated using fuzzy VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR).
Findings
The most important criterion was found as collection cost, followed by pollution prevention and control, storage/holding cost and greenhouse gas emissions in collection and classification of e-waste. Autonomous tools were found as the best smart technology for collection and classification of e-waste, followed by robotics and smart vehicles.
Originality/value
The originality of the study is to propose a framework, which integrates the collection and classification of e-waste and smart technologies.
Details
Keywords
Jagdeep Singh and Harwinder Singh
The purpose of this paper is to review the literature and provide an overview of the history, evolution and existing research on continuous improvement (CI). It reviews a large…
Abstract
Purpose
The purpose of this paper is to review the literature and provide an overview of the history, evolution and existing research on continuous improvement (CI). It reviews a large number of research papers in this field and presents the overview of various CI implementation practices demonstrated by manufacturing organizations globally.
Design/methodology/approach
The paper systematically categorizes the published literature, analyzes and reviews it methodically.
Findings
The paper reveals the important concepts, case studies and surveys in concerned with CI methodology. The contributions of CI programmes towards improving manufacturing performance of the organizations and CI values that underlies continuous improvement have also been highlighted.
Practical implications
The literature on classification of CI has so far been very limited. The paper reviews a large number of papers in this field and presents the overview of various CI practices demonstrated by manufacturing organizations globally. Further the future implications have also been discussed for the smooth and effective implementation of CI practices in manufacturing organizations.
Originality/value
The paper contains a comprehensive listing of publications on the field in question and their classification. It will be useful to researchers, professionals and others concerned with this subject to understand the significance of CI methodology.
Details
Keywords
Wanbin Pan, Xinyue Chen, Wei Liu, Lixian Qiao, Haiying Kuang and Wen Feng Lu
This study aims to improve the stiffness of as-printed handles by finding appropriate printing orientations.
Abstract
Purpose
This study aims to improve the stiffness of as-printed handles by finding appropriate printing orientations.
Design/methodology/approach
First, a series of benchmark handles is designed using Taguchi method. Then, for each uniformly sampled printing orientation, every benchmark handle is sliced and undergoes stiffness evaluation (i.e. displacement and mean stress) by using finite element analysis (FEA). This generates a substantial batch of handle-orientation-stiffness samples. With the data, an effective stiffness-prediction network is developed based on the artificial neural network. Finally, using the developed network, the particle swarm optimization is adapted to determine the optimized printing orientation for each input handle, aiming to improve its stiffness.
Findings
Compared with the common slicing software, the printing orientations proposed in this study, based on FEA, result in varying degrees of improvement in stiffness for four handles. Specifically, the displacement and mean stress are reduced by 16.86% and 18.14% on average. The experiments show that the approach has the potential to effectively improve the stiffness of a handle.
Originality/value
Although the anisotropic property in mechanics is unavoidable and difficult to formally describe in 3D printing, the proposed approach can effectively characterize the relationship between the stiffness and the printing orientation for each handle. And, it also can determine an optimized printing orientation for each handle to enhance its stiffness after printing.