Term Frequency-inverse Research Articles

Sentiment Analysis and Twitter Social Media Visualization Regarding the Omnibus Law Draft

This study will classify Twitter users' positive and negative opinions about the omnibus method using a frequency-inverse document frequency algorithm and a multi-layer perceptron method. The sentiment analysis process involves several stages, including B. Collecting and preprocessing data, calculating term weights using inverse term frequencies and document frequencies, and classifying data using multi-layer perceptrons. Additionally, the study visually represents Twitter's sentiment analysis results on the omnibus method. These visualizations include word cloud, top accounts, tweet frequency, hashtags, and sentiment. Three scenarios were considered to perform the classification experiments. Scenario 1 used 700 training data, scenario 2 used 800, and Scenario 3 used 900 training data. The findings show that the Term Frequency Inverse Document Frequency algorithm and the multi-layer perceptron method are adequate for sentiment analysis, with Scenario 3 yielding the highest accuracy rate of 88%.

Analysis of online parenting community posts on expanded newborn screening for metabolic disorders using topic modeling: a quantitative content analysis.

As more newborns have received expanded newborn screening (NBS) for metabolic disorders, the overall number of false-positive results has increased. The purpose of this study was to explore the psychological impacts experienced by mothers related to the NBS process. An online parenting community in Korea was selected, and questions regarding NBS were collected using web crawling for the period from October 2018 to August 2021. In total, 634 posts were analyzed. The collected unstructured text data were preprocessed, and keyword analysis, topic modeling, and visualization were performed. Of 1,057 words extracted from posts, the top keyword based on 'term frequency-inverse document frequency' values was "hypothyroidism," followed by "discharge," "close examination," "thyroid-stimulating hormone levels," and "jaundice." The top keyword based on the simple frequency of appearance was "XXX hospital," followed by "close examination," "discharge," "breastfeeding," "hypothyroidism," and "professor." As a result of LDA topic modeling, posts related to inborn errors of metabolism (IEMs) were classified into four main themes: "confirmatory tests of IEMs," "mother and newborn with thyroid function problems," "retests of IEMs," and "feeding related to IEMs." Mothers experienced substantial frustration, stress, and anxiety when they received positive NBS results. The online parenting community played an important role in acquiring and sharing information, as well as psychological support related to NBS in newborn mothers. Nurses can use this study's findings to develop timely and evidence-based information for parents whose children receive positive NBS results to reduce the negative psychological impact.

Adaptive Rider Feedback Artificial Tree Optimization-Based Deep Neuro-Fuzzy Network for Classification of Sentiment Grade

Sentiment analysis is an efficient technique for expressing users’ opinions (neutral, negative or positive) regarding specific services or products. One of the important benefits of analyzing sentiment is in appraising the comments that users provide or service providers or services. In this work, a solution known as adaptive rider feedback artificial tree optimization-based deep neuro-fuzzy network (RFATO-based DNFN) is implemented for efficient sentiment grade classification. Here, the input is pre-processed by employing the process of stemming and stop word removal. Then, important factors, e.g. SentiWordNet-based features, such as the mean value, variance, as well as kurtosis, spam word-based features, term frequency-inverse document frequency (TF-IDF) features and emoticon-based features, are extracted. In addition, angular similarity and the decision tree model are employed for grouping the reviewed data into specific sets. Next, the deep neuro-fuzzy network (DNFN) classifier is used to classify the sentiment grade. The proposed adaptive rider feedback artificial tree optimization (A-RFATO) approach is utilized for the training of DNFN. The A-RFATO technique is a combination of the feedback artificial tree (FAT) approach and the rider optimization algorithm (ROA) with an adaptive concept. The effectiveness of the proposed A-RFATO-based DNFN model is evaluated based on such metrics as sensitivity, accuracy, specificity, and precision. The sentiment grade classification method developed achieves better sensitivity, accuracy, specificity, and precision rates when compared with existing approaches based on Large Movie Review Dataset, Datafiniti Product Database, and Amazon reviews.

TF-TDA: A Novel Supervised Term Weighting Scheme for Sentiment Analysis

In text classification tasks, such as sentiment analysis (SA), feature representation and weighting schemes play a crucial role in classification performance. Traditional term weighting schemes depend on the term frequency within the entire document collection; therefore, they are called unsupervised term weighting (UTW) schemes. One of the most popular UTW schemes is term frequency–inverse document frequency (TF-IDF); however, this is not sufficient for SA tasks. Newer weighting schemes have been developed to take advantage of the membership of documents in their categories. These are called supervised term weighting (STW) schemes; however, most of them weigh the extracted features without considering the characteristics of some noisy features and data imbalances. Therefore, in this study, a novel STW approach was proposed, known as term frequency–term discrimination ability (TF-TDA). TF-TDA mainly presents the extracted features with different degrees of discrimination by categorizing them into several groups. Subsequently, each group is weighted based on its contribution. The proposed method was examined over four SA datasets using naive Bayes (NB) and support vector machine (SVM) models. The experimental results proved the superiority of TF-TDA over two baseline term weighting approaches, with improvements ranging from 0.52% to 3.99% in the F1 score. The statistical test results verified the significant improvement obtained by TF-TDA in most cases, where the p-value ranged from 0.0000597 to 0.0455.

Development of a patients’ satisfaction analysis system using machine learning and lexicon-based methods

BackgroundPatients’ rights are integral to medical ethics. This study aimed to perform sentiment analysis and opinion mining on patients’ messages by a combination of lexicon-based and machine learning methods to identify positive or negative comments and to determine the different ward and staff names mentioned in patients’ messages.MethodsThe level of satisfaction and observance of the rights of 250 service recipients of the hospital was evaluated through the related checklists by the evaluator. In total, 822 Persian messages, composed of 540 negative and 282 positive comments, were collected and labeled by the evaluator. Pre-processing was performed on the messages and followed by 2 feature vectors which were extracted from the messages, including the term frequency–inverse document frequency (TFIDF) vector and a combination of the multifeature (MF) (a lexicon-based method) and TFIDF (MF + TFIDF) vectors. Six feature selectors and 5 classifiers were used in this study. For the evaluations, 5-fold cross-validation with different metrics including area under the receiver operating characteristic curve (AUC), accuracy (ACC), F1 score, sensitivity (SEN), specificity (SPE) and Precision-Recall Curves (PRC) were reported. Message tag detection, which featured different hospital wards and identified staff names mentioned in the study patients’ messages, was implemented by the lexicon-based method.ResultsThe best classifier was Multinomial Naïve Bayes in combination with MF + TFIDF feature vector and SelectFromModel (SFM) feature selection (ACC = 0.89 ± 0.03, AUC = 0.87 ± 0.03, F1 = 0.92 ± 0.03, SEN = 0.93 ± 0.04, and SPE = 0.82 ± 0.02, PRC-AUC = 0.97). Two methods of assessment by the evaluator and artificial intelligence as well as survey systems were compared.ConclusionOur results demonstrated that the lexicon-based method, in combination with machine learning classifiers, could extract sentiments in patients’ comments and classify them into positive and negative categories. We also developed an online survey system to analyze patients’ satisfaction in different wards and to remove conventional assessments by the evaluator.

A machine learning approach to identifying suicide risk among text-based crisis counseling encounters.

With the increasing utilization of text-based suicide crisis counseling, new means of identifying at risk clients must be explored. Natural language processing (NLP) holds promise for evaluating the content of crisis counseling; here we use a data-driven approach to evaluate NLP methods in identifying client suicide risk. De-identified crisis counseling data from a regional text-based crisis encounter and mobile tipline application were used to evaluate two modeling approaches in classifying client suicide risk levels. A manual evaluation of model errors and system behavior was conducted. The neural model outperformed a term frequency-inverse document frequency (tf-idf) model in the false-negative rate. While 75% of the neural model's false negative encounters had some discussion of suicidality, 62.5% saw a resolution of the client's initial concerns. Similarly, the neural model detected signals of suicidality in 60.6% of false-positive encounters. The neural model demonstrated greater sensitivity in the detection of client suicide risk. A manual assessment of errors and model performance reflected these same findings, detecting higher levels of risk in many of the false-positive encounters and lower levels of risk in many of the false negatives. NLP-based models can detect the suicide risk of text-based crisis encounters from the encounter's content.

Dynamic perceived quality analysis using social media data at macro- and micro-levels

PurposeThis paper aims to propose a method for dynamic product perceived quality analysis using social media data and to achieve a macro–micro combination analysis. The method enables the prioritization of perceived quality attributes and provides perception causes.Design/methodology/approachTo rationalize the macro–micro combination, ANOVA and multiple linear regression were used to identify the main factors affecting perceived quality which served as the combination basis; by using the combination basis for consumer segmentation, macro-knowledge (i.e. attribute importance and quality category of the attribute) is achieved by term frequency-inverse document frequency (TF-IDF)-based attribute importance calculation and KANO-based attribute classification, which is combined with micro-quality diagnostic information (i.e. perceived quality, perception causes and quality parameters). Further, dynamic perception Importance-Performance Analysis (IPA) is built to present the attribute priority and perception causes.FindingsThe framework was validated by the new energy vehicle (NEV) data of Autohome. The results show that price and purchase purpose are the most influential factors of perceived quality and that dynamic perception IPA can effectively prioritize attributes and mine perception causes.Originality/valueThis is one of the first studies to analyze dynamic perceived quality using social media data, which contributes to the research on perceived quality. The paper also contributes by achieving a combined macro–micro analysis of perceived quality. The method rationalizes the macro–micro combination by identifying the factors influencing perceived quality, which provides ideas for other studies using social media data.

Classifying spam emails using agglomerative hierarchical clustering and a topic-based approach

Spam emails are unsolicited, annoying and sometimes harmful messages which may contain malware, phishing or hoaxes. Unlike most studies that address the design of efficient anti-spam filters, we approach the spam email problem from a different and novel perspective. Focusing on the needs of cybersecurity units, we follow a topic-based approach for addressing the classification of spam email into multiple categories. We propose SPEMC-15K-E and SPEMC-15K-S, two novel datasets with approximately 15K emails each in English and Spanish, respectively, and we label them using agglomerative hierarchical clustering into 11 classes. We evaluate 16 pipelines, combining four text representation techniques -Term Frequency-Inverse Document Frequency (TF-IDF), Bag of Words, Word2Vec and BERT- and four classifiers: Support Vector Machine, Näive Bayes, Random Forest and Logistic Regression. Experimental results show that the highest performance is achieved with TF-IDF and LR for the English dataset, with a F1 score of 0.953 and an accuracy of 94.6%, and while for the Spanish dataset, TF-IDF with NB yields a F1 score of 0.945 and 98.5% accuracy. Regarding the processing time, TF-IDF with LR leads to the fastest classification, processing an English and Spanish spam email in 2ms and 2.2ms on average, respectively.

MalVulDroid: Tracing Vulnerabilities from Malware in Android using Natural Language Processing

The Android operating system is often inflicted with mobile malware attacks, which occur due to some system loopholes or vulnerabilities. One malware can exploit numerous vulnerabilities and multiple malware can exploit a single vulnerability, thus, causing many-to-many ( X : Y ) mapping between malware and vulnerability. Therefore, it is crucial to understand malware behaviour to reduce the vulnerabilities. This paper presents the concept of a “MalVulDroid” framework that maps malware to vulnerabilities using a two-dimensional matrix. The many-to-many ( X : Y ) mapping matrix is obtained by using natural language processing techniques such as Bag-of-Words (BoW) leveraging n-gram probability generation and term frequency-inverse document frequency (TF-IDF), in addition to supervised machine learning classifiers such as multilayer perceptron (MLP), a support vector machine (SVM), a ripple down rule learner (RIDOR), and a pruning rule-based classification tree (PART). This study is the first of its kind where malware-to-vulnerability mapping can be leveraged to measure the rigorousness of unknown vulnerabilities and malware during the early phases of application development. The study considers extensive datasets such as Androzoo, AMD, and CICInvesAndMal2019 with 150 malware families and 48,907 malware samples, and nine major vulnerabilities affecting Android. MalVulDroid exhibits highly promising results with an accuracy of 98.04% for unigrams, and precision and F1-scores of over 90% using ensemble classifiers.

Sentiment Analysis for IMDb Movie Review Using Support Vector Machine (SVM) Method

Many researchers currently employ supervised, machine learning methods to study sentiment analysis. Analysis can be done on movie reviews, Twitter reviews, online product reviews, blogs, discussion forums, Myspace comments, and social networks. Support Vector Machines (SVM) classifiers are used to analyze the Twitter data set using different parameters. The analysis and discussion were undertaken to allow for the conclusion that SVM has been successfully implemented utilizing the IMDb data for this study (Support Vector Machine). To complete this study, the preprocessing phase, which consisted of filtering and classifying data using SVM with a total of 50.000 data points, was completed after collecting up to 40.000 reviews to use as training data and 10.000 reviews to use as testing data. 25.000 positive and 25.000 negative points make up the view. In this study, we adopted an evaluation matrix including accurate, precision, recall, and F1-score. According to the experiment report, our model achieved SVM with Bags of Word (BoW) used to get results for the highest accuracy test, which was 88,59% accurate. Then, using grid-search, optimize against the SVM parameters to find the best parameters that SVM models can use. Our model achieved Term Frequency–inverse Document Frequency (TF-IDF) was used to get results for the highest accuracy test, which was 91,27% accurate.

Performance evaluation of machine learning models on large dataset of android applications reviews.

With an ever-increasing number of mobile users, the development of mobile applications (apps) has become a potential market during the past decade. Billions of users download mobile apps for divergent use from Google Play Store, fulfill tasks and leave comments about their experience. Such reviews are replete with a variety of feedback that serves as a guide for the improvement of existing apps and intuition for novel mobile apps. However, application reviews are challenging and very broad to approach. Such reviews, when segregated into different classes guide the user in the selection of suitable apps. This study proposes a framework for analyzing the sentiment of reviews for apps of eight different categories like shopping, sports, casual, etc. A large dataset is scrapped comprising 251661 user reviews with the help of 'Regular Expression' and 'Beautiful Soup'. The framework follows the use of different machine learning models along with the term frequency-inverse document frequency (TF-IDF) for feature extraction. Extensive experiments are performed using preprocessing steps, as well as, the stats feature of app reviews to evaluate the performance of the models. Results indicate that combining the stats feature with TF-IDF shows better performance and the support vector machine obtains the highest accuracy. Experimental results can potentially be used by other researchers to select appropriate models for the analysis of app reviews. In addition, the provided dataset is large, diverse, and balanced with eight categories and 59 app reviews and provides the opportunity to analyze reviews using state-of-the-art approaches.

A New Tool for Holistic Residency Application Review: Using Natural Language Processing of Applicant Experiences to Predict Interview Invitation.

Reviewing residency application narrative components is time intensive and has contributed to nearly half of applications not receiving holistic review. The authors developed a natural language processing (NLP)-based tool to automate review of applicants' narrative experience entries and predict interview invitation. Experience entries (n = 188,500) were extracted from 6,403 residency applications across 3 application cycles (2017-2019) at 1 internal medicine program, combined at the applicant level, and paired with the interview invitation decision (n = 1,224 invitations). NLP identified important words (or word pairs) with term frequency-inverse document frequency, which were used to predict interview invitation using logistic regression with L1 regularization. Terms remaining in the model were analyzed thematically. Logistic regression models were also built using structured application data and a combination of NLP and structured data. Model performance was evaluated on never-before-seen data using area under the receiver operating characteristic and precision-recall curves (AUROC, AUPRC). The NLP model had an AUROC of 0.80 (vs chance decision of 0.50) and AUPRC of 0.49 (vs chance decision of 0.19), showing moderate predictive strength. Phrases indicating active leadership, research, or work in social justice and health disparities were associated with interview invitation. The model's detection of these key selection factors demonstrated face validity. Adding structured data to the model significantly improved prediction (AUROC 0.92, AUPRC 0.73), as expected given reliance on such metrics for interview invitation. This model represents a first step in using NLP-based artificial intelligence tools to promote holistic residency application review. The authors are assessing the practical utility of using this model to identify applicants screened out using traditional metrics. Generalizability must be determined through model retraining and evaluation at other programs. Work is ongoing to thwart model "gaming," improve prediction, and remove unwanted biases introduced during model training.

Tuning Language Processing Approaches for Pashto Texts Classification

Nowadays, text classification for different purposes becomes a basic task for concerned people. Hence, much research has been done to develop automatic text classification for the majority of national and international languages. However, the need for an automated text classification system for local languages is felt. The main purpose of this study is to establish a novel automatic classification system of Pashto text. In order to follow this up, we established a collection of Pashto documents and constructed the dataset. In addition, this study includes several models containing statistical techniques and neural network neural machine learning including DistilBERT-base-multilingual-cased, Multilayer Perceptron, Support Vector Machine, K Nearest Neighbor, decision tree, Gaussian naïve Bayes, multinomial naïve Bayes, random forest, and logistic regression to discover the most effective approach. Moreover, this investigation evaluates two different feature extraction methods including bag of words, and Term Frequency Inverse Document Frequency. Subsequently, this research obtained an average testing accuracy rate of 94% using the MLP classification algorithm and TFIDF feature extraction method in single label multi-class classification. Similarly, MLP+TFIDF with F1-measure of 0.81 showed the best result. Experiments on the use of pre-trained language representation models (such as DistilBERT) for classifying Pashto texts show that we need a specific tokenizer for a particular language to obtain reasonable results.

Temporal analysis and opinion dynamics of COVID-19 vaccination tweets using diverse feature engineering techniques.

The outbreak of the COVID-19 pandemic has also triggered a tsunami of news, instructions, and precautionary measures related to the disease on social media platforms. Despite the considerable support on social media, a large number of fake propaganda and conspiracies are also circulated. People also reacted to COVID-19 vaccination on social media and expressed their opinions, perceptions, and conceptions. The present research work aims to explore the opinion dynamics of the general public about COVID-19 vaccination to help the administration authorities to devise policies to increase vaccination acceptance. For this purpose, a framework is proposed to perform sentiment analysis of COVID-19 vaccination-related tweets. The influence of term frequency-inverse document frequency, bag of words (BoW), Word2Vec, and combination of TF-IDF and BoW are explored with classifiers including random forest, gradient boosting machine, extra tree classifier (ETC), logistic regression, Naïve Bayes, stochastic gradient descent, multilayer perceptron, convolutional neural network (CNN), bidirectional encoder representations from transformers (BERT), long short-term memory (LSTM), and recurrent neural network (RNN). Results reveal that ETC outperforms using BoW with a 92% of accuracy and is the most suitable approach for sentiment analysis of COVID-19-related tweets. Opinion dynamics show that sentiments in favor of vaccination have increased over time.

Real-time Twitter Sentiment Analysis for Moroccan Universities using Machine Learning and Big Data Technologies

In recent years, sentiment analysis (SA) has raised the interest of researchers in several domains, including higher education. It can be applied to measure the quality of the services supplied by the higher education institution and construct a university ranking mechanism from social media like Twitter. Hence, this study presents a novel system for Twitter sentiment prediction on Moroccan public universities in real-time. It consists of two phases: offline sentiment analysis phase and real-time prediction phase. In the offline phase, the collected French tweets about twelve Moroccan universities were classified according to their sentiment into ‘positive’, ‘negative’, or ‘neutral’ using six machine learning algorithms (random forest, multinomial Naive Bayes classifier, logistic regression, decision tree, linear support vector classifier, and extreme gradient boosting) with the term frequency-inverse document frequency (TF-IDF) and count vectorizer feature extraction techniques. The results reveal that random forest classifier coupled with TF-IDF has obtained the best test accuracy of 90%. This model was then applied on real-time tweets. The real-time prediction pipeline comprises Twitter streaming API for data collection, Apache Kafka for data ingestion, Apache Spark for real-time sentiment analysis, Elasticsearch for real-time data exploration, and Kibana for data visualization. The obtained results can be used by the Ministry of higher education, scientific research and innovation of Morocco for decision-making process.

Evaluating the Ability of Open-Source Artificial Intelligence to Predict Accepting-Journal Impact Factor and Eigenfactor Score Using Academic Article Abstracts: Cross-sectional Machine Learning Analysis

Strategies to improve the selection of appropriate target journals may reduce delays in disseminating research results. Machine learning is increasingly used in content-based recommender algorithms to guide journal submissions for academic articles. We sought to evaluate the performance of open-source artificial intelligence to predict the impact factor or Eigenfactor score tertile using academic article abstracts. PubMed-indexed articles published between 2016 and 2021 were identified with the Medical Subject Headings (MeSH) terms "ophthalmology," "radiology," and "neurology." Journals, titles, abstracts, author lists, and MeSH terms were collected. Journal impact factor and Eigenfactor scores were sourced from the 2020 Clarivate Journal Citation Report. The journals included in the study were allocated percentile ranks based on impact factor and Eigenfactor scores, compared with other journals that released publications in the same year. All abstracts were preprocessed, which included the removal of the abstract structure, and combined with titles, authors, and MeSH terms as a single input. The input data underwent preprocessing with the inbuilt ktrain Bidirectional Encoder Representations from Transformers (BERT) preprocessing library before analysis with BERT. Before use for logistic regression and XGBoost models, the input data underwent punctuation removal, negation detection, stemming, and conversion into a term frequency-inverse document frequency array. Following this preprocessing, data were randomly split into training and testing data sets with a 3:1 train:test ratio. Models were developed to predict whether a given article would be published in a first, second, or third tertile journal (0-33rd centile, 34th-66th centile, or 67th-100th centile), as ranked either by impact factor or Eigenfactor score. BERT, XGBoost, and logistic regression models were developed on the training data set before evaluation on the hold-out test data set. The primary outcome was overall classification accuracy for the best-performing model in the prediction of accepting journal impact factor tertile. There were 10,813 articles from 382 unique journals. The median impact factor and Eigenfactor score were 2.117 (IQR 1.102-2.622) and 0.00247 (IQR 0.00105-0.03), respectively. The BERT model achieved the highest impact factor tertile classification accuracy of 75.0%, followed by an accuracy of 71.6% for XGBoost and 65.4% for logistic regression. Similarly, BERT achieved the highest Eigenfactor score tertile classification accuracy of 73.6%, followed by an accuracy of 71.8% for XGBoost and 65.3% for logistic regression. Open-source artificial intelligence can predict the impact factor and Eigenfactor score of accepting peer-reviewed journals. Further studies are required to examine the effect on publication success and the time-to-publication of such recommender systems.

Modified term frequency-inverse document frequency based deep hybrid framework for sentiment analysis.

Sentiment Analysis is a highly crucial subfield in Natural Language Processing that attempts to extract the public sentiment from the accessible user opinions. This paper proposes a hybridized neural network based sentiment analysis framework using a modified term frequency-inverse document frequency approach. After preprocessing of data, the basic term frequency-inverse document frequency scheme is improved by introducing a non-linear global weighting factor. This improved scheme is combined with the k-best selection method to vectorize textual features. Next, the pre-trained embedding technique is employed for the mathematical representation of the textual features to process them efficiently by the Deep Learning methodologies. The embedded features are then passed to the deep neural network, consisting of Convolutional Neural Network and Long Short Term Memory. Convolutional Neural Networks can build hierarchical representations for capturing locally embedded features within the feature space, and Long Short Term Memory tries to recall useful historical information for sentiment polarization. This deep neural network finally provides the sentiment label. The proposed model is compared with different state-of-the-art baseline models in terms of various performance metrics using several datasets to demonstrate its efficacy.

Where are your ideas going? Idea adoption in online user innovation communities

PurposeWith the proliferation of ideas submitted by users in firm-built online user innovation communities, community managers are faced with the problem of user idea overload. The purpose of this paper is to explore the influencing factors on the idea adoption to identify high quality ideas, and then propose a method to quickly filter high value ideas.Design/methodology/approachThe authors collected more than 110,000 data submitted by Xiaomi community users and analyzed the factors affecting idea adoption using a multinomial logistic regression model. In addition, the authors also used BP neural network to predict the idea adoption process.FindingsThe empirical results show that idea semantics, number of likes, number of comments, number of related posts, the existence of pictures and self-presentation have positive impact on idea adoption, while idea length and idea timeliness had negative impact on idea adoption. In addition, this paper calculates the idea evaluation value through the idea adoption process predicted by neural network and the mean value of idea term frequency inverse document frequency (TF-IDF).Originality/valueThis empirical study expands the theoretical perspective of idea adoption research by using dual-process theory and enriches the research methods in the field of idea adoption research through the multinomial logistic regression method. Based on our findings, firms can quickly identify valuable ideas and effectively alleviate the information overload problem of online user innovation communities.

An evaluation of a computational technique for measuring the embeddedness of sustainability in the curriculum aligned to AASHE-STARS and the United Nations Sustainable Development Goals

IntroductionSDG 4.7 mandates university contributions to the United Nations (UN) Sustainable Development Goals (SDGs) through their education provisions. Hence, universities increasingly assess their curricular alignment to the SDGs. A common approach to the assessment is to identify keywords associated with specific SDGs and to analyze for their presence in the curriculum. An inherent challenge is associating the identified keywords as used in the diverse set of curricular contexts to relevant sustainability indicators; hence, the urgent need for more systematic assessment as SDG implementation passes its mid-cycle.MethodIn this study, a more nuanced technique was evaluated with notable capabilities for: (i) computing the importance of keywords based on the term frequency-inverse document frequency (TF-IDF) method; (ii) extending this computation to the importance of courses to each SDG and; (iii) correlating such importance to a statistical categorization based on the Association for the Advancement of Sustainability in Higher Education (AASHE) criteria. Application of the technique to analyze 5,773 modules in a university's curriculum portfolio facilitated categorization of the modules/courses to be “sustainability-focused” or “sustainability-inclusive.” With the strategic objective of systematically assessing the sustainability content of taught curricula, it is critical to evaluate the precision and accuracy of the computed results, in order to attribute text with the appropriate SDGs and level of sustainability embeddedness. This paper evaluates this technique, comparing its results against a manual and labor-intensive interpretation of expert informed assessment of sustainability embeddedness on a random sample of 306 modules/courses.Results and discussionExcept for SDGs 1 and 17, the technique exhibited a reasonable degree of accuracy in predicting module/course alignment to SDGs and in categorizing them using AASHE criteria. Whilst limited to curricular contexts from a single university, this study indicates that the technique can support curricular transformation by stimulating enhancement and reframing of module/course contexts through the lens of the SDGs.

Design of a Compliance Index for Privacy Policies: A Study of Mobile Wallet and Remittance Services

Many nations have adopted comprehensive data privacy laws to protect customers’ data. However, privacy policies of mobile wallet digital payment systems (DPS), and particularly the mobile wallet and remittance services that are part of DPS, are often not compliant with privacy laws. There is a lack of measures to assess how adequate the policies are in addressing data privacy issues. To address this problem, this article develops a compliance index to help DPS organizations assess the compliance of their privacy policies with the general data protection regulation (GDPR). The compliance index is created through a natural language process that includes term frequency-inverse document frequency matrix and topic modeling using latent Dirichlet allocation, to compute 1) an emphasis density score that indicates the level of emphasis a privacy policy places on GDPR dimensions, and 2) a privacy score that identifies the level of compliance of a privacy policy with GDPR. The compliance index is validated by assessing its effectiveness at the country level in comparison with an international publicly available data privacy benchmark.