Lexicon-based Techniques Research Articles

A Stacking Ensemble Based on Lexicon and Machine Learning Methods for the Sentiment Analysis of Tweets

Sentiment is employed in various fields, such as collecting web-based opinions for the formulation of governmental policies, measuring employee and customer satisfaction levels in business organizations, and measuring the sentiment of the public in political and security matters. The field has recently faced new challenges since algorithms must operate with highly unstructured sentiment data from social media. In this study, the authors present a new stacking ensemble method that combines the lexicon-based approach with machine learning algorithms to improve the sentiment analysis of tweets. Due to the complexity of the text with very ill-defined syntactic and grammatical patterns, using lexicon-based techniques to extract sentiment from the content is proposed. On the same note, the contextual and nuanced aspects of sentiment are inferred through machine learning algorithms. A sophisticated bat algorithm that uses an Elman network as a meta-classifier is then employed to classify the extracted features accurately. Substantial evidence from three datasets that are readily available for public analysis re-affirms the improvements this innovative approach brings to sentiment classification.

Reviewing the effectiveness of lexicon-based techniques for sentiment analysis in massive open online courses

Reviewing the effectiveness of lexicon-based techniques for sentiment analysis in massive open online courses

Emotional Intelligence in Academic Decision-Making: A Systematic Review of Sentiment Mining Approaches

This study aims to investigate and understand the importance of the intersection of Emotional Intelligence and academic decision-making through a systematic review of sentiment mining approaches. Recognizing the pivotal role of emotions in shaping educational choices, this paper explores the theoretical foundations of emotional intelligence and the integration of sentiment-mining methodologies within academic contexts. In this study, an extensive literature review is conducted focusing on emotional intelligence within the education sector, as well as exploring sentiment mining approaches. In the existing literature review, the researchers have introduced various machine learning and lexicon-based techniques, significantly contributing to the advancement of emotional intelligence in the education sector for higher studies. The findings contribute to the role of emotional intelligence in shaping academic decisions, providing valuable insights for educational practitioners. This study shows a direct relationship between emotional intelligence and decision-making within the educational sector

Exploring sentiment analysis of online food delivery services post COVID-19 pandemic: grabfood and foodpanda

ABSTRACT This study aims to explore the sentiment of consumer experience regarding two popular online food delivery services: GradFood and Foodpanda. RapidMiner is used to scrape and analyze tweets from X (formerly known as Twitter) using the VADER lexicon-based technique and applied manual content analysis to identify the themes related to customer experience. A sample of tweets from GrabFood and Foodpanda was collected from January 2021 to November 2021 through the X’s Application Programming Interface (API). This study gathered and analyzed 1300 tweets for GrabFood and 1073 tweets for Foodpanda. Then, manual content analysis is applied to identify the themes related to customer experience for GrabFood and Foodpanda. Findings showed that GrabFood and Foodpanda got the highest proportion of positive sentiment compared to negative sentiment. However, GrabFood has received more positive sentiments as compared to FoodPanda. The content analysis revealed 12 prevalent themes that customers focused on are “promote,” “reward,” “service,” “advice,” “customer experience,” “cancellation,” “time,” “apps issues,” “customer service,” “price” and “others.” This study provides a unique insight into customer experience toward online food delivery services. These findings can help online food service delivery management to monitor service quality, marketing strategy and customer expectations. The decision maker can better decide which aspects they should pay more attention to related to the positive and negative sentiment requirement.

Sentiment Analysis Approaches and Applications - A Review

With the advent of smartphones and the ease of access to the internet, people are mainly interested in sending textual messages through social media platforms. In many cases, customers would like to review the services provided by different providers in order to express satisfaction or dissatisfaction. The sentiments of users make a huge difference in the success of any business idea in the present digital age. As there are many competitors in every field of technology, health, and education, people would selectively want to use the resources that have positive opinions about them from the user community in the online reviews. There are different techniques to effectively estimate the user reviews, whether they are for or against a particular concept or the product. There are different techniques, like lexicon-based techniques, machine learning-based techniques, and deep learning-based techniques which are used to analyse the sentiments of the users’ reviews in order to improve user expectations. Lexicon-based techniques have many challenges, like the wrong interpretation of the meanings of the words and giving wrong sentiment scores to the words used by ignoring the grammatical constraints in the user reviews. There are many machine learning algorithms, like Logistic regression (LR), and Support Vector Machines (SVM) which can overcome the shortcomings of lexicon-based sentiment analysis models and could be used in various spheres of applications. The manuscript presents a detailed study in this regard.

Leveraging social media data using latent dirichlet allocation and naïve bayes for mental health sentiment analytics on Covid-19 pandemic

In Malaysia, during the early stages of the COVID-19 pandemic, the negative impact on mental health became noticeable. The public's psychological and behavioral responses have risen as the COVID-19 outbreak progresses. A high impression of severity, vulnerability, impact, and fear was the element that influenced higher anxiety. Social media data can be used to track Malaysian sentiments in the COVID-19 era. However, it is often found on the internet in text format with no labels, and manually decoding this data is usually complicated. Furthermore, traditional data-gathering approaches, such as filling out a survey form, may not completely capture the sentiments. This study uses a text mining technique called Latent Dirichlet Allocation (LDA) on social media to discover mental health topics during the COVID-19 pandemic. Then, a model is developed using a hybrid approach, combining both lexicon-based and Naïve Bayes classifier. The accuracy, precision, recall, and F-measures are used to evaluate the sentiment classification. The result shows that the best lexicon-based technique is VADER with 72% accuracy compared to TextBlob with 70% accuracy. These sentiments results allow for a better understanding and handling of the pandemic. The top three topics are identified and further classified into positive and negative comments. In conclusion, the developed model can assist healthcare workers and policymakers in making the right decisions in the upcoming pandemic outbreaks.

Using social media and personality traits to assess software developers' emotional polarity.

Although human factors (e.g., cognitive functions, behaviors and skills, human error models, etc.) are key elements to improve software development productivity and quality, the role of software developers' emotions and their personality traits in software engineering still needs to be studied. A major difficulty is in assessing developers' emotions, leading to the classic problem of having difficulties understanding what cannot be easily measured. Existing approaches to infer emotions, such as facial expressions, self-assessed surveys, and biometric sensors, imply considerable intrusiveness on developers and tend to be used only during normal working periods. This article proposes to assess the feasibility of using social media posts (e.g., developers' posts on Twitter) to accurately determine the polarity of emotions of software developers over extended periods in a non-intrusive manner, allowing the identification of potentially abnormal periods of negative or positive sentiments of developers that may affect software development productivity or software quality. Our results suggested that Twitter data can serve as a valid source for accurately inferring the polarity of emotions. We evaluated 31 combinations of unsupervised lexicon-based techniques using a dataset with 79,029 public posts from Twitter from sixteen software developers, achieving a macro F1-Score of 0.745 and 76.8% of accuracy with the ensemble comprised of SentiStrength, Sentilex-PT, and LIWC2015_PT lexicons. Among other results, we found a statistically significant difference in tweets' polarities posted during working and non-working periods for 31.25% of the participants, suggesting that emotional polarity monitoring outside working hours could also be relevant. We also assessed the Big Five personality traits of the developers and preliminarily used them to ponder the polarities inferences. In this context, Openness, Conscientiousness, and Extraversion were frequently related to neutral and positive posts, while Neuroticism is associated with negative posts. Our results show that the proposed approach is accurate enough to constitute a simple and non-intrusive alternative to existing methods. Tools using this approach can be applied in real software development environments to support software team workers in making decisions to improve the software development process.

Correction of whitespace and word segmentation in noisy Pashto text using CRF

Word segmentation is the process of splitting up the text into words. In English and most European languages, word boundaries are identified by whitespace, while in Pashto, there is no explicit word delimiter. Pashto uses whitespace for word separation but not consistently, and it cannot be considered a reliable word-boundary identifier. This inconsistency makes the Pashto word segmentation unique and challenging. Moreover, Pashto is a low-resource, non-standardized language with no established rules for the correct usage of whitespace that leads to two typical spelling errors, space-omission, and space-insertion. These errors significantly affect the performance of the word segmenter. This study aims to develop a state-of-the-art word segmenter for Pashto, with a proofing tool to identify and correct the position of space in a noisy text. The CRF algorithm is incorporated to train two machine learning models for these tasks. For models' training, we have developed a text corpus of nearly 3.5 million words, annotated for the correct positions of spaces and explicit word boundary information using a lexicon-based technique, and then manually checked for errors. The experimental results of the model are very satisfactory, where the F1-scores are 99.2% and 96.7% for the proofing model and word segmenter, respectively.

Categorization of Arabic posts using Artificial Neural Network and hash features

Sentiment analysis is an important study topic with diverse application domains including social network monitoring and automatic analysis of the body of natural language communication. Existing research on sentiment analysis has already utilised substantial domain knowledge available online comprising users’ opinion in various areas such as business, education, and social media. There is however limited literature available on Arabic language sentiment analysis. Furthermore, datasets used in majority of these studies have poor classification. In the present study, we utilised a primary dataset comprising 2122 sentences and 15,331 words compiled from 206 publicly available online posts to perform sentiment classification by using advanced machine learning technique based on Artificial Neural Networks. Unlike lexicon-based techniques that suffer from low accuracy due to their computational nature and parameter configuration, Artificial Neural Networks were used to classify people opinion posts into three categories including conservative, reform and revolution, accompanied by multiple hasher vector size to benchmark the performance of the proposed model. Extensive simulation results indicated an accuracy of 93.33%, 100%, and 100% for the classification of conservation, reform, and revolutionary classes, respectively.

Sentiment Analysis of COVID-19 Tweets Using Deep Learning and Lexicon-Based Approaches

Social media is a platform where people communicate, share content, and build relationships. Due to the current pandemic, many people are turning to social networks such as Facebook, WhatsApp, Twitter, etc., to express their feelings. In this paper, we analyse the sentiments of Indian citizens about the COVID-19 pandemic and vaccination drive using text messages posted on the Twitter platform. The sentiments were classified using deep learning and lexicon-based techniques. A lexicon-based approach was used to classify the polarity of the tweets using the tools VADER and NRCLex. A recurrent neural network was trained using Bi-LSTM and GRU techniques, achieving 92.70% and 91.24% accuracy on the COVID-19 dataset. Accuracy values of 92.48% and 93.03% were obtained for the vaccination tweets classification with Bi-LSTM and GRU, respectively. The developed models can assist healthcare workers and policymakers to make the right decisions in the upcoming pandemic outbreaks.

Sentiment Analysis of Text Reviews Using Lexicon-Enhanced Bert Embedding (LeBERT) Model with Convolutional Neural Network

Sentiment analysis has become an important area of research in natural language processing. This technique has a wide range of applications, such as comprehending user preferences in ecommerce feedback portals, politics, and in governance. However, accurate sentiment analysis requires robust text representation techniques that can convert words into precise vectors that represent the input text. There are two categories of text representation techniques: lexicon-based techniques and machine learning-based techniques. From research, both techniques have limitations. For instance, pre-trained word embeddings, such as Word2Vec, Glove, and bidirectional encoder representations from transformers (BERT), generate vectors by considering word distances, similarities, and occurrences ignoring other aspects such as word sentiment orientation. Aiming at such limitations, this paper presents a sentiment classification model (named LeBERT) combining sentiment lexicon, N-grams, BERT, and CNN. In the model, sentiment lexicon, N-grams, and BERT are used to vectorize words selected from a section of the input text. CNN is used as the deep neural network classifier for feature mapping and giving the output sentiment class. The proposed model is evaluated on three public datasets, namely, Amazon products’ reviews, Imbd movies’ reviews, and Yelp restaurants’ reviews datasets. Accuracy, precision, and F-measure are used as the model performance metrics. The experimental results indicate that the proposed LeBERT model outperforms the existing state-of-the-art models, with a F-measure score of 88.73% in binary sentiment classification.

Automated Classification of Societal Sentiments on Twitter With Machine Learning

The rapid growth in information sharing on social media has defined a new information age in our society. Microblogging sites, such as Twitter, gained immense popularity during the COVID-19 pandemic. We developed an automated framework to extract the positive, negative, and neutral sentiments from tweets, and to further classify the tweets through machine-learning (ML) techniques. The developed framework can help to understand the sentiments in our society during profound events, such as the COVID-19 pandemic. Our framework is novel in that it is a hybrid framework that combines a lexicon-based technique for tweet sentiment analysis and labeling with supervised ML techniques for tweet classification. We have evaluated the hybrid framework with a range of measures, such as precision, accuracy, recall, and F1 score. Our results indicate that the majority of the sentiments are positive (38.5%) or neutral (34.7%). Furthermore, with an accuracy of 83%, the long short-term memory (LSTM) neural network has been selected as the preferred ML technique in the framework. The evaluation results indicate that our hybrid framework has the potential to automatically classify large tweet volumes, such as the tweets on COVID-19, according to the sentiments in the society.

Sentiment Analysis in Hindi—A Survey on the State-of-the-art Techniques

Sentiment Analysis (SA) has been a core interest in the field of text mining research, dealing with computational processing of sentiments, views, and subjective nature of the text. Due to the availability of extensive web-based data in Indian languages such as Hindi, Marathi, Kannada, Tamil, and so on. It has become extremely significant to analyze this data and recover valuable and relevant information. Hindi being the first language of the majority of the population in India, SA in Hindi has turned out to be a critical task particularly for companies and government organizations. This research portrays a systematic review specifically in the field of Hindi SA. The major contribution of this article includes the categorization of numerous articles based on techniques that have attracted researchers in performing SA tasks in Hindi language. This survey classifies these state-of-the-art computational intelligence techniques into four major categories namely lexicon-based techniques, machine learning techniques, deep learning techniques, and hybrid techniques. It discusses the importance of these techniques based on different aspects such as their impact on the issues of SA, levels of analysis, and performance evaluation measures. The research puts forward a comprehensive overview of the majority of the work done in Hindi SA. This study will help researchers in finding out resources such as annotated datasets, linguistic resources, and lexical resources. This survey delivers some significant findings and presents overall future research directions in the field of Hindi SA.

Health, Psychosocial, and Social Issues Emanating From the COVID-19 Pandemic Based on Social Media Comments: Text Mining and Thematic Analysis Approach.

BackgroundThe COVID-19 pandemic has caused a global health crisis that affects many aspects of human lives. In the absence of vaccines and antivirals, several behavioral change and policy initiatives such as physical distancing have been implemented to control the spread of COVID-19. Social media data can reveal public perceptions toward how governments and health agencies worldwide are handling the pandemic, and the impact of the disease on people regardless of their geographic locations in line with various factors that hinder or facilitate the efforts to control the spread of the pandemic globally.ObjectiveThis paper aims to investigate the impact of the COVID-19 pandemic on people worldwide using social media data.MethodsWe applied natural language processing (NLP) and thematic analysis to understand public opinions, experiences, and issues with respect to the COVID-19 pandemic using social media data. First, we collected over 47 million COVID-19–related comments from Twitter, Facebook, YouTube, and three online discussion forums. Second, we performed data preprocessing, which involved applying NLP techniques to clean and prepare the data for automated key phrase extraction. Third, we applied the NLP approach to extract meaningful key phrases from over 1 million randomly selected comments and computed sentiment score for each key phrase and assigned sentiment polarity (ie, positive, negative, or neutral) based on the score using a lexicon-based technique. Fourth, we grouped related negative and positive key phrases into categories or broad themes.ResultsA total of 34 negative themes emerged, out of which 15 were health-related issues, psychosocial issues, and social issues related to the COVID-19 pandemic from the public perspective. Some of the health-related issues were increased mortality, health concerns, struggling health systems, and fitness issues; while some of the psychosocial issues were frustrations due to life disruptions, panic shopping, and expression of fear. Social issues were harassment, domestic violence, and wrong societal attitude. In addition, 20 positive themes emerged from our results. Some of the positive themes were public awareness, encouragement, gratitude, cleaner environment, online learning, charity, spiritual support, and innovative research.ConclusionsWe uncovered various negative and positive themes representing public perceptions toward the COVID-19 pandemic and recommended interventions that can help address the health, psychosocial, and social issues based on the positive themes and other research evidence. These interventions will help governments, health professionals and agencies, institutions, and individuals in their efforts to curb the spread of COVID-19 and minimize its impact, and in reacting to any future pandemics.

Determining the Efficiency of Drugs Under Special Conditions From Users’ Reviews on Healthcare Web Forums

Sentiment analysis is the extraction and categorization of sentiments that have been expressed in text data using text analysis techniques. Manifested by earlier studies, sentiment analysis of drug reviews has a large potential for providing valuable insights to assist healthcare professionals and companies for evaluating the safety of drugs after it has been marketed. Such insights help safeguard patients and increase their trust in medical companies. The existing systems either follow a lexicon-based approach or a learning-based approach for sentiment analysis in the medical domain. Learning-based techniques require annotated data while lexicon-based techniques tend to be domain-specific which restricts their wide use. This research embarks on a hybrid technique that utilizes both learning-based and lexicon-based approaches to achieve better results. General-purpose sentiment lexicons, such as AFFIN, TextBlob, and VADER, are used for annotating the reviews. Furthermore, several feature engineering techniques, such as term frequency (TF), term frequency-inverse document frequency (TF-IDF), and union of TF and TF-IDF (TF U TF-IDF) have been incorporated for the extraction of useful features. Finally, the learning models including logistic regression (LR), AdaBoost classifier (AB), random forest (RF), extra tree classifier (ETC), and multilayer perceptron (MLP) are used to classify sentiments of the reviews. The performance of the proposed hybrid approach is evaluated using accuracy, precision, recall, and F1-score. Experimental results indicate that the combination of learning-based and lexicon-based approaches provide improved results than their individual use. Moreover, TextBlob has shown promising results giving an accuracy of 96% with MLP when used with TF-IDF and with LR when used with TF U TF-IDF.

Sentiment Analysis of Student’s Opinion on Programming Assessment: Evaluation of Naïve Bayes over Support Vector Machines

This study investigates the performance of machine learning algorithms for sentiment analysis of students’ opinions on programming assessment. Previous researches show that Support Vector Machines (SVM) performs the best among all techniques, followed by Naïve Bayes (NB) in sentiment analysis. This study proposes a framework for classifying sentiments, as positive or negative using NB algorithm and Lexicon-based approach on small data set. The performance of NB algorithm was evaluated using SVM. NB and SVM conquer the Lexicon-based approach opinion lexicon technique in terms of accuracy in the specific area for which it is trained. The Lexicon-based technique, on the other hand, avoids difficult steps needed to train the classifier. Data was analyzed from 75 first year undergraduate students in School of Computing, Universiti Teknologi Malaysia taking programming subject. The student’s sentiments were gathered based on their opinions for the zero-score policy for unsuccessful compilation of program during skill-based test. The result of the study reveals that the students tend to have negative sentiments on programming assessment as it gives them scary emotions. The experimental result of applying NB algorithm yields a prediction accuracy of 85% which outperform both the SVM with 70% and Lexicon-based approach with 60% accuracy. The result shows that NB works better than SVM and Lexicon-based approach on small dataset.

An Enhanced Sentiment Analysis Framework Based on Pre-Trained Word Embedding

Sentiment analysis (SA) is a technique that lets people in different fields such as business, economy, research, government, and politics to know about people’s opinions, which greatly affects the process of decision-making. SA techniques are classified into: lexicon-based techniques, machine learning techniques, and a hybrid between both approaches. Each approach has its limitations and drawbacks, the machine learning approach depends on manual feature extraction, lexicon-based approach relies on sentiment lexicons that are usually unscalable, unreliable, and manually annotated by human experts. Nowadays, word-embedding techniques have been commonly used in SA classification. Currently, Word2Vec and GloVe are some of the most accurate and usable word embedding techniques, which can transform words into meaningful semantic vectors. However, these techniques ignore sentiment information of texts and require a huge corpus of texts for training and generating accurate vectors, which are used as inputs of deep learning models. In this paper, we propose an enhanced ensemble classifier framework. Our framework is based on our previously published lexicon-based method, bag-of-words, and pre-trained word embedding, first the sentence is preprocessed by removing stop-words, POS tagging, stemming and lemmatization, shortening exaggerated word. Second, the processed sentence is passed to three modules, our previous lexicon-based method (Sum Votes), bag-of-words module and semantic module (Word2Vec and Glove) and produced feature vectors. Finally, the previous features vectors are fed into 11 different classifiers. The proposed framework is tested and evaluated over four datasets with five different lexicons, the experiment results show that our proposed model outperforms the previous lexicon based and the machine learning methods individually.

Modified fuzzy sentiment analysis approach based on user ranking suitable for online social networks

The rapidly increasing of sentiment analysis in social networks has lead business owners and decision makers to value opinion leaders who can influence people's impressions concerning certain business or commodity. Nevertheless, decision makers are being misled by inaccurate results due to the ignorance of perspectivism. Considering perspectivism, while computing text polarity, can help machines to reflect the human perceived sentiment within the content. This emphasises the need for integrating social behaviour (user's influence factor) with sentiment analysis (text polarity scores), providing a more pragmatic portrayal of how the writer's audience comprehend the message. In this study, a new model is proposed to intensify sentiment analysis process on Twitter. In the achievement of such, social network analysis is done using UCINET tool followed by artificial neural networks for ranking users. For sentiment classification, a hybrid approach is presented, where lexicon-based technique is combined with a fuzzy classification technique to handle language vagueness as well as for an inclusive analysis of tweets into seven classes; for the purpose of enhancing final results. The proposed model is practiced on data collected from Twitter. Results show a significant enhancement in tweets polarity scores represent more realistic sentiments.

Fine grain sentiment grading of user-generated big data using contextual cues

With a tremendous growth in the use of online resources, micro-blogging website like Twitter offers a vast amount of user-generated knowledge about marketing. This knowledge can be used for sentiment analysis and finds wide application in both public and private sectors. A novel two-tier classification framework using machine learning algorithms and lexicon-based algorithm is proposed to extract sentiment of tweets and assign a fine grain grade to the tweets among one of the seven classes namely: high negative, moderate negative, low negative, neutral, low positive, moderate positive and high positive. Context is also used by forming SentiCircles for the task of sentiment classification. The evaluation of the study shows that the proposed method provides fine grain grading to tweets with accuracy of 61.84%. The hybrid machine learning and lexicon-based processing technique with the usage of contextual cues is an effective and practical method for sentiment analysis.

SHOTGUN: converting words into triplets

Software systems convert between graphemes and phonemes using lexicon-based, rule-based or data-driven techniques. SHOTGUN combines these techniques in a hybrid system which converts between graphemes and phonemes bi-directionally, adds linguistic and educational information about the relationships between graphemes and phonemes and provides estimates about the likelihood that the generated output is correct. We describe the components from which SHOTGUN is built and determine its accuracy by running tests on two data sources, the BasisSpellingBank and CELEX, comparing the results to Nunn’s (1998) rule-based conversion system. SHOTGUN converts phonemes to graphemes and vice versa with precision of 81% and 86% when tested on the BasisSpellingBank, and 80% and 81% when tested on CELEX. SHOTGUN proves to be a powerful new conversion tool.