Sentemonet: A Comprehensive Framework for Multimodal Sentiment Analysis from Text and Emotions

In recent years, ride-hailing platforms such as Uber have significantly transformed the transportation industry by offering convenient, flexible, and technology-driven services. These platforms have made travel more accessible by enabling users to book rides instantly through mobile applications. However, customer satisfaction is not always consistent, as users frequently report issues related to pricing, driver behavior, service reliability, and application performance. Understanding these concerns is essential for improving service quality and enhancing user experience.This study focuses on analyzing customer reviews collected from Uber using sentiment analysis techniques. Since customer feedback is typically unstructured and large in volume,manual analysis is inefficient. Therefore, Natural Language Processing (NLP) techniques are used to process and interpret the textual data. The research applies both machine learning and deep learning models, including Logistic Regression, Naïve Bayes, Random Forest, and Long Short-Term Memory (LSTM), to classify reviews into positive, negative, and neutral sentiments. The dataset used in this study consists of approximately 12,000 customer reviews, which provide a diverse representation of user experiences. Data preprocessing techniques such as cleaning, tokenization, stopword removal, and stemming are applied to improve data quality. The experimental results demonstrate that deep learning models, particularly LSTM,outperform traditional machine learning approaches in terms of accuracy and contextual understanding. The proposed model achieved an overall accuracy of 90%, indicating its effectiveness in correctly classifying customer sentiments. The analysis also reveals key factors influencing customer satisfaction, including frequent ride cancellations, surge pricing, driver-related issues, and technical problems within the application. Overall, this research highlights the importance of sentiment analysis as a powerful tool for understanding customer opinions in ride-hailing platforms. The insights obtained from this study can help companies make data-driven decisions, improve service quality, and enhance customer satisfaction.

Text mining is a special case of data mining which explore unstructured or semi-structured text documents, to establish valuable patterns and rules that indicate trends and significant features about specific topics. Text mining has been in pattern recognition, predictive studies, sentiment analysis and statistical theories in many areas of research, medicine, financial analysis, social life analysis, and business intelligence. Text mining uses concept of natural language processing and machine learning. Machine learning algorithms have been used and reported to give great results, but their performance of machine learning algorithms is affected by factors such as dataset domain, number of classes, length of the corpus, and feature selection techniques used. Redundant attribute affects the performance of the classification algorithm, but this can be reduced by using different feature selection techniques and dimensionality reduction techniques. Feature selection is a data preprocessing step that chooses a subset of input variable while eliminating features with little or no predictive information. Feature selection techniques are Information gain, Term Frequency, Term Frequency-Inverse document frequency, Mutual Information, and Chi-Square, which can use a filters, wrappers, or embedded approaches. To get the most value from machine learning, pairing the best algorithms with the right tools and processes is necessary. Little research has been done on the effect of feature selection techniques on classification accuracy for pairing of these algorithms with the best feature selection techniques for optimal results. In this research, a text classification experiment was conducted using incident management dataset, where incidents were classified into their resolver groups. Support vector machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes (NB) and Decision tree (DT) machine learning algorithms were examined. Filtering approach was used on the feature selection techniques, with different ranking indices applied for optimal feature set and classification accuracy results analyzed. The classification accuracy results obtained using TF were, 88% for SVM, 70% for NB, 79% for Decision tree, and KNN had 55%, while Boolean registered 90%, 83%, 82% and 75%, for SVM, NB, DT, and KNN respectively. TF-IDF, had 91%, 83%, 76%, and 56% for SVM, NB, DT, and KNN respectively. The results showed that algorithm performance is affected by feature selection technique applied. SVM performed best, followed by DT, KNN and finally NB. In conclusion, presence of noisy data leads to poor learning performance and increases the computational time. The classifiers performed differently depending on the feature selection technique applied. For optimal results, the classifier that performed best together with the feature selection technique with the best feature subset should be applied for all types of data for accurate classification performance. Keywords: Text Classification, Supervised Machine Learning, Feature Selection DOI : 10.7176/JIEA/9-3-06 Publication date :May 31 st 2019

Introduction Large language models (LLMs) have the potential to realize accurate risk stratification and disease prediction by integrating multimodal data, such as electronic health records, medical images, and genomic profiles. However, in complex tasks like atherosclerosis risk estimation, the design of the prompt is critical to bring out the performance of LLMs. Several researches have demonstrated that in-context learning, where the prompt contains some cases, improves the performance of LLMs when the contained cases are carefully selected. Because manual selection usually requires enormous costs, automatic case selection has been desired. Methods This study aims to improve the effectiveness of in-context learning in LLM for atherosclerosis risk prediction by introducing a strategy for case selection. Our method involves two key components: feature selection and case selection. In the feature selection phase, we compute the mutual information between the clinical features and atherosclerosis risk using the database to extract the essential clinical features. This feature selection removes the unimportant features that disturb the performance of the case selection mechanism. Then, in the case selection phase, we select several cases from the database that are the most similar to the patient being diagnosed. This study compares three metrics to compute the similarity score: - Mahalanobis distance (trained via large margin nearest neighbor classification; LMNN [1]) - Cosine similarity (between the vector representations in KNN-augmented in-context example selection; KATE [2]) - Euclidean distance (between the prompt features) This combined strategy supplies the LLM with informative cases and thereby enhances the diagnostic performance. Results We used a fine-tuned Llama3-8B model for our target language and analyzed a dataset of 117,709 cases. Each case contained 96 features that were collected from annual health check-up data. From this dataset, 1,000 cases each were randomly selected for validation and test datasets. The remaining data were used as the database in our system. We considered a binary classification task and assigned the positive label when the Cardio-Ankle Vascular Index (CAVI) was greater than 8.0. The proportion of selected features was adjusted in 10% increments to maximize the F1 score on the validation dataset. The result shows that our proposed method, the strategic feature and case selections, significantly improved the F1 score for the test dataset by around 2% compared with zero-shot prompt and random selection (see the attached table). Among three similarity metrics, Euclidean distance yielded the highest F1 scores. We also observed that the feature selection phase with the adjusted number of selected features improved the F1 score in almost all settings. Conclusion Our strategy for feature and case selections improved the performance of in-context learning for LLM-based atherosclerosis risk prediction.

Sentiment analysis is widely used today to make data-driven decisions in different industries, starting from marketing and including brand management, reputation monitoring, and customer satisfaction analysis. Its growing importance is closely linked with so-called ‘word-of-mouth’ communication, from reading online reviews to writing comments on social networks. Effective separation of sentiments ensures that companies' responses are timely and critical patterns are seen in big data sets. Statistical measures, information gain, correlation-based approaches, etc, have been employed for the feature selection. Still, the problem associated with text data mining is that they don’t convey the text's relative difficulty and additional features. To fill this gap, our research proposes a new feature selection technique through Ant Colony Optimization (ACO) and K Nearest Neighbour (KNN) performed on 28,000 customer reviews in different product categories. The results, therefore, showed an overall accuracy of 80.1%, with the Support Vector Machine (SVM) set at 80.5% on each selected feature, which was slightly higher than the Convolutional Neural Network (CNN), which scored a 78.41% accuracy. SVM remains on the mark of 83%, and for CNN, the rate achieved on the same was 80.8% when both were applied to the entire dataset. These facts rejected the infallibility of the simple and complex algorithms used singly in the sentiment classification, indicating that more sophisticated algorithms like ACO and KNN can provide business solutions to improve their service delivery based on customers’ feedback.

Sentiment Analysis (SA) and opinion mining is used for the systems of business intelligence in analyzing public opinion towards various brands and implementing market strategies. Machine learning aims at developing the algorithm in such a way that the performance of a system is optimized with past data or experience. In the case of SA, the feature selection method is used for the identification of different goals such as reduction of cost of computation, avoidance of over-fitting, and enhancing the accuracy of classification of the model. The methods of feature selection can reduce their original feature sets by the removal of irrelevant features for the classification of text sentiment and their accuracy. The paper surveys various feature selection techniques available in the literature. The study shows that feature selection significantly improves the classification of the sentiments, but it depends on the technique adopted and the number of features selected.

Customers' sentiment on food delivery services: An Arabic text mining approach

Introduction: The early and accurate detection of COVID-19 remains a life-threatening challenge in medical analysis. Machine learning is used for predicting disease outcomes based on clinical parameters. This analysis proposes a comparative analysis of feature selection method and classification techniques to enhance COVID-19 detection accuracy using blood biomarkers. We used a pensourse dataset of 1,724 cases, including 35 features. To improve the model performance data preprocessing process included outlier handling, normalization, and transformation techniques to improve model performance. To identify the relevant features, we employed the three-feature selection methods Chi-Square test, Pearson correlation coefficient, and Random Forest. The model prediction accuracy was enhanced using a stacking ensemble classication techniques. The machine learning based classification models effectively predicted COVID-19 infectious disease using blood biomarkers with optimized feature selection techniques. Objectives: To enhance the accuracy of COVID-19 prediction using machine learning techniques by applying feature selection and classification techniques on blood biomarkers. Methods: The comparative analysis utilized a publicly available dataset containing 1,724 cases with 35 attributes. Data preprocessing involved outlier handling, normalization, and transformation techniques. Employed Chi-Square test, Pearson correlation coefficient, and Random Forest feature selection techniques. Stacking ensemble classification algorithm was utilized for the better performance of a model. Results: The classification models demonstrated efficiency in predicting COVID-19 using blood biomarkers. Optimized feature selection significantly improved predictive accuracy, highlighting the importance of selecting relevant features for model performance enhancement. Conclusions: This study showcases the potential of ML-driven approaches for COVID-19 detection, emphasizing the role of feature selection in improving classification accuracy. The findings contribute to the advancement of diagnostic tools, offering a data-driven solution for rapid and reliable COVID-19 screening.

Credit risk assessment is an essential task for financial institutions, as it evaluates the likelihood of loan defaults. Misclassifying loan applications can result in substantial economic losses. However, accurately predicting customers' creditworthiness presents challenges for machine learning models due to high dimensionality and imbalanced class distributions, which can severely impact overall model performance. This implements three feature selection (FS) techniques, such as Random Forest with Highly Correlated features (RFHC), Information Gain, and Chi-Square to address the high dimensional problem. Additionally, SMOTE is implemented to address the imbalanced dataset. The model performance is analyzed using three different approaches. First, employing only feature selection techniques, in the second approach, we employed feature selection followed by oversampling, and in the final approach, oversampling prior to feature selection is employed. The experimental results indicate that implementing feature selection followed by oversampling gives better performance compared to the other two approaches. Among the feature selection techniques, RFHC outperforms the others, achieving a highest F1-score of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{95.12 \%}$</tex> and an AUC value of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{85.76 \%}$</tex>.

User-generated content, such as product and app reviews, offers more than just sentiment. It provides a rich spectrum of emotional expression that reveals users’ experiences, frustrations and expectations. Traditional sentiment analysis, which typically classifies text as positive or negative, lacks the nuance needed to fully understand the emotional drivers behind customer feedback. In this research, we focus on fine-grained emotion classification using core emotions. By identifying specific emotions rather than sentiment polarity, we enable more actionable insights for e-commerce and app development, supporting strategies such as feature refinement, marketing personalization and proactive customer engagement. We leverage the Hugging Face Emotions dataset and adopt a two-phase modeling approach. In the first phase, we use a pre-trained DistilBERT model as a feature extractor and evaluate multiple classical classifiers (Logistic Regression, Support Vector Classifier, Random Forest) to establish performance baselines. In the second phase, we fine-tune the DistilBERT model end-to-end using the Hugging Face Trainer API, optimizing classification performance through task-specific adaptation. Training is tracked using the Weights &amp; Biases (wandb) API. Comparative analysis highlights the substantial performance gains from fine-tuning, particularly in capturing informal or noisy language typical in user reviews. The final fine-tuned model is applied to a dataset of customers’ reviews, identifying the dominant emotions expressed. Our results demonstrate the practical value of emotion-aware analytics in uncovering the underlying “why” behind user sentiment, enabling more empathetic decision-making across product design, customer support and user experience (UX) strategy.

Sentiment analysis in its simplest form is the classification of a piece of text into positive or negative class based on the polarity of the text. Horoscopes consist of future predictions for each of the twelve zodiac signs and are very popular in India. All major TV channels and newspapers publish their horoscope expert's predictions on a daily basis. These daily horoscopes are well suited for the task of sentiment analysis as they have a high percentage of strong sentiment bearing sentences. This work deals with sentiment analysis of Bengali daily horoscope. A corpus of 6000 sentences is created by crawling through the website of a leading Bengali newspaper's daily horoscope section. Each sentence is annotated with polarity (positive or negative) by a team of three independent annotators. A lexicon of 58 stop words is also created from the frequently occurring words in the corpus. A comparative analysis of five well known classification algorithms namely Naive Bayes, Support Vector Machines, k-Nearest Neighbours, Decision Tree and Random Forest is done. For each classification algorithm three different input features (unigram, bigram and trigram presence) are experimented with. Stop word removal and feature selection using information gain metric are also used. SVM with all unigram features neither removing stop words nor using information gain metric for feature selection proves to be the best combination producing an accuracy of 98.7%.

Identifying important biomarkers to improve disease diagnosis and treatment is a significant topic of research in bioinformatics. However, bioinformatics datasets frequently have a large number of features per sample or instance. This problem, known as “high dimensionality,” can be alleviated through the use of dimension reducing techniques such as feature (gene) selection which remove unnecessary features. There are many versions of feature selection, with varying biases and predictive abilities. However, predictive power is but one factor to consider when choosing a feature selection technique: one must also consider the technique's stability, that is, its ability to create feature subsets which remain valid in the face of changes to the data. While there has been work in determining the relative stability of different feature selection techniques, this does not always help determine whether a chosen feature selection technique will give stable feature subsets for a specific dataset. Factors such as difficulty of learning (e.g., dataset difficulty) may also influence feature selection stability, making generally-true facts about different techniques not applicable to a given dataset. In this work, we study how dataset difficulty can affect the stability of feature selection techniques, leading to good performance from bad techniques and vice versa. We use a set of twenty-six DNA microarray datasets with varying levels of difficulty of learning, along with four levels of dataset perturbation, six feature selection techniques with various levels of stability, and twelve feature subset sizes. The results show that as the dataset difficulty increases, the stability decreases. However, the relative stability between the techniques remains the same. Additionally, the more difficult the dataset, the more the stability is affected by changes to the data. We also found that unstable rankers are more affected by the transition between Easy and Moderate datasets, whereas the stable techniques are more affected by the change between Moderate and Hard datasets. Lastly, as the feature subset size increases, the stability increases and the difference between the levels of dataset difficulty decreases. Overall, we conclude that difficulty of learning must be taken into account before interpreting stability results.

Sentiment analysis (SA) is used to identify the person’s opinion from unstructured information. It is broadly applied to predict stock market movement direction to recognize the public opinion towards a company or products. The conventional techniques designed for SA do not provide higher accuracy, which impacts the reliability of stock market prediction. In order to improve the prediction performance, a Gensim Lovins Truncative Morisita–Horn’s Broken-stick Regression-based Recursive deep neural network (GLTMBR-RDNN) is introduced for predicting the future outcomes in the stock market with a lesser error rate and minimal time. The customer reviews are collected from a large database. The GLTMBR-RDNN includes different layers for learning the input reviews. In the GLTMBR-RDNN technique, the first preprocessing of the text is carried out in the first hidden layer by removing stop words, stem words, truncation and so on. First, the Gensim tokenizer is applied in the preprocessing step to partition the text into a number of words. The proposed GLTMBR-RDNN technique uses a Sklearned model for stop word removal. Followed by Lovins truncative stemming process is carried out in the preprocessing step. Finally, the Normalization process is done for transforming the words into a standard form. After preprocessing, Morisita–Horn’s Broken-stick Regression process is performed in the second hidden layer for predicting the future stock market value based on the classification of customer reviews by setting the breakpoint to the similarity score between the reviews. In this way, future stock market values are efficiently identified with enhanced classification accuracy in the output layer. The result of the suggested GLTMBR-RDNN technique is analyzed using metrics such as accuracy, F-measure, precision, recall and prediction time based on various input reviews. The results prove that the introduced GLTMBR-RDNN technique improves the performance of accuracy with less prediction time when compared to existing methods.

An essential function of natural language processing is sentiment analysis. Which holds substantial significance in understanding public opinion across diverse domains. However, while sentiment analysis methodologies abound in English, there exists a notable scarcity of research addressing sentiment analysis in languages like Hindi. In response, the above paper provides a pioneering aspect to Hindi sentiment analysis through the development of a hybrid deep learning-machine learning model integrated with a metaheuristic optimization algorithm. By amalgamating the strengths for normal machine learning (ML) techniques and deep learning (DL), this model endeavours to boost accuracy and robustness in sentiment classification tasks specific to Hindi text. Furthermore, the inclusion of a metaheuristic optimization algorithm aims to optimize crucial model parameters, thereby improving convergence speed and overall performance. The proposed approach is motivated by the need for more comprehensive sentiment analysis techniques tailored for multilingual social media data, particularly in languages like Hindi, which are prevalent on various online platforms. Through empirical evaluation and comparative analysis, this paper demonstrates the efficacy and potential applications of the proposed hybrid model in real-world sentiment analysis scenarios. This research contributes to bridging the gap in sentiment analysis research for non-English languages and lays the foundation for further advancements in multilingual sentiment analysis methodologies.

Opinion mining is important in text mining applications in brand and product positioning, consumer attitude detection, customer relationship management and market research. Applications result in new generation companies, products for reputation management, online market perception and online content monitoring. Web expansion encourages users to contribute or express opinions through blogs, videos and social networking sites which provide information for sentiment analysis regarding a product or service. This study investigates various feature extraction methods performance and opinion mining classification algorithm. Evaluation is through the use of opinions from amazon.com with product reviews. Features extraction is from opinions using Term Document Frequency and Inverse Document Frequency (TDF×IDF). Feature transformation is through Principal Component Analysis (PCA) and kernel PCA. Feature selection techniques like Information Gain (IG), Mutual Information (MI) and Fisher Score select features. Extracted features are classified by Naïve Bayes, k Nearest Neighbour and Classification and Regression Trees (CART) classification algorithms.

Today, video data, as a powerful multimedia component, is accompanied by some problems with increasing usage in communication, health, education, and social media in particular. Classification and detection of concepts in video data by automatic methods are some of these challenging problems. In this study, we propose a video classification system, which incorporates deep convolutional neural networks (CNNs) by leveraging feature selection and data fusion techniques to improve the accuracy of the classification. Principal Component Analysis (PCA) as a feature selection method and Discriminant Correlation Analysis (DCA) technique, which incorporates class associations into the correlation analysis of feature sets for data fusion, are applied to the problem at the feature level. Support Vector Machines (SVMs) have been trained with new feature vectors obtained from different deep convolutional neural networks by feature selection and data fusion methods. The proposed method is tested for 38 concepts on TRECVID 2013 SIN video task dataset and the results are evaluated. Our results show that the classification accuracy is improved by 4% with an accuracy of 50.27% when the proposed data fusion and feature selection techniques are used.