Bloom-epistemic and sentiment analysis hierarchical classification in course discussion forums

As digital marketing is becoming more popular, the number of customer views on brands is increasing rapidly. This makes it harder for companies to assess their brand image or digitally market their products on the web. We present a lexicon-based approach to extracting sentiment and emotion from tweets for digital marketing purposes. We collect ten thousand tweets related to ten technology brands: Apple, Google, Microsoft, Samsung, GE, IBM, Intel, Facebook, Oracle and HP. We perform sentiment analysis using SentiWordNet while we detect emotions using the NRC Hashtag Emotion Lexicon. We compare and combine the scores obtained from the two lexicons into one result per tweet. We describe the execution process of our experiment and show that the accuracy of the combined approach of sentiment and emotion analysis is enhanced over the independent approaches of sentiment analysis or emotion analysis.

Understanding and comprehending humans' views, beliefs, attitudes, or opinions toward a particular entity is sentiment analysis (SA). Advancements in e‐commerce platforms has led to an abundance of the real‐time and free forms of opinions floating on social media platforms. This real‐world data are imprecise and vague hence fuzzy logic is required to deal with such subjective data. Since opinions can be fuzzy in nature and definitions of opinion words can be elucidated differently; fuzzy logic has witnessed itself as an effective method to capture the expression of opinions. The study presents an elaborate review of the around 170 published research works for SA using fuzzy logic. The primary emphasis is focused on text‐based SA, audio‐based SA, and fusion of text‐audio features‐based SA. This article discusses the various novel ways of classifying fuzzy logic‐based SA research articles, which have not been accomplished by any other review article till date. The article puts forward the importance of SA tasks and identifies how fuzzy logic adds to this importance. Finally, the article outlines a taxonomy for sentiment classification based on the technique‐supervised and unsupervised in the SA models and comprehensively reviews the SA approaches specific to their task. Prominently, this study highlights the suitability of fuzzy‐based SA approaches into five different classes vis‐a‐vis (a) Sentiment Cognition from Words using fuzzy logic, (b) Sentiment Cognition from Phrases using fuzzy logic, (c) Fuzzy‐rule based SA, (d) Neuro‐fuzzy network‐based SA, and (e) Fuzzy Emotion Recognition.This article is categorized under:Algorithmic Development > Text MiningFundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining

The investigation studied the state of art on corpus-based approaches for sentiment analysis. Thus, detailing its methodologies, evaluation metrics, limitations, and future directions. The importance of sentiment analysis in fields such as marketing, customer feedback analysis, social media monitoring, financial analysis, and political science is emphasized. The methodology for corpus-based approaches in sentiment analysis includes the following key steps: data collection, preprocessing, feature extraction, and sentiment classification. The lexicon-based approaches include the corpus-based or bag of words (BOW) and dictionary (also called opinion lexicon). Evaluation of the corpus-based sentiment analysis approach is addressed through performance metrics such as accuracy, precision, recall, F1-score, and comparative analysis with other approaches including hybrid and rule-based systems. Limitations of corpus-based sentiment analysis, such as data sparsity and domain adaptation, are acknowledged, alongside potential enhancements and research directions including ensemble learning, deep learning architectures, and multimodal data integration. The conclusion emphasizes the versatility and scalability of corpus-based sentiment analysis, while ongoing research efforts aim to address its limitations and further enhance its applicability in diverse domains.

In the recent years opinion mining plays an important role by business analyst before launching a product. Opinion mining mainly concerns about detecting and extracting the feature from various opinion rich resources like review sites, discussion forum, blogs and news corpora so on. The data obtained from those are highly unstructured in nature and very large in volume, therefore data preprocessing plays an essential role in sentiment analysis. Researchers are trying to develop newer algorithm. This research paper attempts to develop a better opinion mining algorithm and the performance has been worked out.

Objective: To make an extensive analysis of sentiment within the discourse surrounding COVID-19 vaccines on Twitter, employing Natural Language Processing (NLP) methodologies. Method: The research methodology encompasses data collection via the Twitter API, followed by sentiment analysis facilitated by the TextBlob library. Pre-processing stages are integrated to cleanse and standardize the Twitter data. Subsequently, sentiment analysis categorizes tweets into positive, negative, and neutral sentiments based on polarity scores. Findings: The findings, grounded in a dataset spanning from March 1, 2022, to April 30, 2022, comprising 61,934 tweets, unveil that 45.0% of tweets conveyed positive sentiment, 17.3% exhibited negativity, and 37.7% maintained neutrality. Moreover, an exploration of tweet subjectivity revealed that 70.1% of the content expressed subjectivity, while 29.9% conveyed objectivity. The research is augmented with visual representations, including word clouds and subjectivity-polarity graphs, that offer a more intuitive understanding of sentiment trends. Novelty: This study contributes to the expanding landscape of sentiment analysis and its application within the context of public health crises, empowering stakeholders with valuable knowledge to enhance vaccine acceptance and effectiveness. The tool used “Tweet Downloader” in data collection makes this study different from other reviewed studies. Keywords: COVID-19 vaccine, Twitter sentiment analysis, Public perception, Natural Language Processing (NLP), Social media data

Sentiment analysis has emerged as a powerful tool in financial markets, offering the ability to harness market participants' collective wisdom and emotions to make more informed investment decisions. This research paper presents a comprehensive literature review on sentiment analysis models in predicting stock prices, focusing on the Bank Nifty Index, a critical benchmark in the Indian financial sector. The review begins by elucidating the significance of sentiment analysis in stock price prediction, highlighting its pivotal role in capturing market sentiment, investor emotions, and their impact on asset valuations. A detailed overview of sentiment sources, encompassing financial news, social media, reports, and other relevant data streams, provides insight into the rich tapestry of information that sentiment analysis can leverage. The paper delves into various sentiment analysis approaches, from traditional lexicon-based and rule-based methods to cutting-edge machine learning and deep learning techniques. It elucidates the intricate process of integrating sentiment analysis with stock price prediction models, exploring feature concatenation, time series integration, and weighted data to incorporate sentiment insights effectively. Evaluation metrics crucial for assessing the performance of both sentiment analysis models and stock price prediction models are thoroughly discussed. It concludes by highlighting the substantial potential of sentiment analysis in augmenting stock price prediction, offering investors and traders valuable tools to navigate the complexities of financial markets.

In natural language processing (NLP), Sentiment analysis is flourishing rapidly as it aims at finding the emotional tone behind a piece of text and helps in understanding the attitudes, opinions, and emotions expressed within an online mention. The internet is flooded with large amounts of data such as texts, photos, audio, and video. With the help of sentiment analysis, we can find useful information from this data. This paper presents various approaches in sentiment analysis used by researchers and the major challenges faced in this field. By analyzing different papers, we came to know that the most widely used techniques in machine learning are Naïve Bayes and SVM and in NLP, the lexicon-based approach is used. With the advancement in technology, sentiment analysis will be available for the public and smaller companies as well.

Sentiment analysis (SA) is a subject of ongoing text mining research. The subjectivity, emotions, and viewpoints of a text are handled algorithmically by sentiment analysis. This survey research examines the most recent development in this field in great detail. This paper examines and provides a quick overview of various recently suggested algorithm enhancements. Based on their contributions to the various sentiment analysis approaches, these articles are categorized into various categories. Sentiment analysis may be utilised to extract information related to thoughts and feelings from human-generated textual data. Users have posted a significant quantity of unprocessed material to social networking sites in the shape of speech, videos, photographs, and audio. Global catastrophes including heatwaves, earthquakes, cyclones, floods and bushfires are having an extraordinary impact on social media users' life. They frequently write how pessimistic they find the catastrophic scenarios at their target area to be. Politicians and strategic planners must prioritise comprehending location-specific attitudes towards crisis situations. Data may be turned into valuable knowledge by using sentiment analysis. The primary goal of the questionnaire is to provide a concise, almost complete picture of Sentiment Analysis methods and associated topics. The comprehensive categories of several recently published papers and the explanation of the present state of research in sentiment evaluation as well as related fields are the key contributions made by this study.

Intelligent systems currently have been proven to provide more benefits on various aspects of human life. One of them is sentiment analysis (SA) approach. SA is a mathematical approach that allows machines to analyze the opinion polarity of the statements or documents. Generally, SA is utilized to observe the tendency of public opinion on an issue. SA can also be used on e-commerce to analyze the trend of customer statements toward a product based on the reviews given by them. Thus, SA will help e-commerce business owners to know the level of acceptance toward offered products. In this paper, we try to evaluate the artificial neural network (ANN) algorithm in conducting a SA of electronic products reviews. In this study, the ANN was designed using 1 input layer, 1 hidden layer consisting of 10 neurons, and 1 output layer consisting of 2 neurons. Our experimental results showed that the ANN had a fairly high accuracy and precision while conducting SA toward electronic products reviews that have been carried out, i.e. 70.80% and 71.07% respectively. Hence, ANN is very possible to be applied to intelligent systems that are tasked to assist e-commerce business owners in conducting SA toward feedback provided by the customers.

Mobile eCommerce applications are increasingly becoming popular for shopping online in Africa, since the means of accessing the Internet is mostly through mobile devices. This presents an opportunity to explore and understand the key issues affecting African mobile eCommerce applications by performing sentiment analysis of users reviews from seven top African mobile eCommerce applications (i.e., Jiji Nigeria, Jumia, Jiji Kenya, Konga, Takealot, KiliMall and Jiji Uganda). We implement two sentiment analysis approaches, which are Linguistic Inquiry Word Count (LIWC) and Machine Learning (ML), to classify user reviews into positive or negative sentiment polarity. Specifically, we compare five ML algorithms and the LIWC with respect to their performance, and also conduct thematic analysis to uncover the positive and negative factors affecting African mobile eCommerce. Our results show that LIWC is the best performing method with 86.7% F1-score. Our thematic analysis reveals various business, legal, and technology issues, as well as positive factors such as ease of use, fast delivery time, and affordable items. Finally, we offer recommendations on how to tackle the negative issues.

Sentiment analysis has become a powerful tool in processing and analysing expressed opinions on a large scale. While the application of sentiment analysis on English-language content has been widely examined, the applications on the Russian language remains not as well-studied. In this survey, we comprehensively reviewed the applications of sentiment analysis of Russian-language content and identified current challenges and future research directions. In contrast with previous surveys, we targeted the applications of sentiment analysis rather than existing sentiment analysis approaches and their classification quality. We synthesised and systematically characterised existing applied sentiment analysis studies by their source of analysed data, purpose, employed sentiment analysis approach, and primary outcomes and limitations. We presented a research agenda to improve the quality of the applied sentiment analysis studies and to expand the existing research base to new directions. Additionally, to help scholars selecting an appropriate training dataset, we performed an additional literature review and identified publicly available sentiment datasets of Russian-language texts.

Emotion detection (ED) and sentiment analysis (SA) play a vital role in identifying an individual’s level of interest in any given field. Humans use facial expressions, voice pitch, gestures, and words to convey their emotions. Emotion detection and sentiment analysis in English and Chinese have received much attention in the last decade. Still, poor-resource languages such as Urdu have been mostly disregarded, which is the primary focus of this research. Roman Urdu should also be investigated like other languages because social media platforms are frequently used for communication. Roman Urdu faces a significant challenge in the absence of corpus for emotion detection and sentiment analysis because linguistic resources are vital for natural language processing. In this study, we create a corpus of 1021 sentences for emotion detection and 20,251 sentences for sentiment analysis, both obtained from various areas, and annotate it with the aid of human annotators from six and three classes, respectively. In order to train large-scale unlabeled data, the bag-of-word, term frequency-inverse document frequency, and Skip-gram models are employed, and the learned word vector is then fed into the CNN-LSTM model. In addition to our proposed approach, we also use other fundamental algorithms, including a convolutional neural network, long short-term memory, artificial neural networks, and recurrent neural networks for comparison. The result indicates that the CNN-LSTM proposed method paired with Word2Vec is more effective than other approaches regarding emotion detection and evaluating sentiment analysis in Roman Urdu. Furthermore, we compare our based model with some previous work. Both emotion detection and sentiment analysis have seen significant improvements, jumping from an accuracy of 85% to 95% and from 89% to 93.3%, respectively.

In an increasingly digital world, opinions and emotions expressed across a variety of online platforms, when analyzed,propose immense potential for businesses, governments, and organizations. Sentiment analysis includes a collection of techniques that provide a fast and efficient way to classify user comments and derive meaningful information. Though sentiment analysis has been in practice for quite some time, there is a significant advancement in terms of approaches used because of increasing amounts of available data in various forms, including text, requirement of contextual understanding, business needs, etc. This article provides a comprehensive review of the latest advancements in sentiment classification in terms of scope, techniques and challenges. This literature review presents a good insight into the classification of various approaches in sentiment analysis and comparative analysis of different techniques. It also highlights the challenges in terms of the research gap and proposes future directions.

Sentiment analysis (SA), generally known as opinion mining (OM), is the process of gathering and evaluating people’s ideas, thoughts, feelings, and beliefs, including views about various subjects, goods, and services. Individuals produce large amounts of comments and evaluations about products, services, and day-to-day tasks as Internet-based applications such as webpages, online sites, social networking sites, and blog posts continue to evolve at a rapid pace. Businesses, governmental organisations, academics, and medical researchers can all utilise sentiment analysis to gather and assess people’s attitudes and viewpoints, get commercial information, and make better decisions. The approaches for sentiment analysis are thoroughly examined in this chapter, including problems, trends, and features, in order to provide academics with a worldwide overview of sentiment analysis and topics of interest. The chapter discusses the various uses of sentiment analysis as well as the general procedure for performing the assignment. The chapter subsequently examines and analyses the various techniques to gain a comprehensive understanding of its benefits and downsides. Furthermore, to elucidate long term prospects, the constraints of sentiment analysis have been highlighted.

As the popularity and accessibility of artificial intelligence (AI) in learning continue to rise, online education has increasingly incorporated AI. It is imperative to investigate how AI in the scholarly community supports the learning of autonomous students. This scoping review investigated articles that employed AI in discussion forums. The objective of this study is to develop a summary that denotes the effective integration of AI in discussion forums, thereby characterizing the overall learning experience. In accordance with the search, appraisal, synthesis, and analysis (SALSA) framework, the preferred reporting items for systematic reviews and meta-analyses (PRISMA) flow diagram was employed to design the article screening and selection process. Scopus was utilized for the literature search, resulting in the identification of twelve articles that met the predetermined inclusion and exclusion criteria. The extracted articles covered the following six applications: intelligent tutoring systems, AI-assisted apps, chatbots, automatic formative assessment, AI teaching assistants, and AI-assisted lifelong learning assistants. Three types of man-machine partnerships related to the activities are discussed: student-AI partnerships, student-AI-student partnerships, and student-AI-teacher partnerships, the latter being the most commonly observed. The generated content was frequently processed through teacher adjustments and checks. Components of community of inquiry theory were adapted as indicators. Cognitive presence was observed to be more predominant than social presence, with a particular emphasis on individual learning achievements. Three distinct perspectives regarding the role of AI in learning were identified. The first perspective posited that AI functioned as a virtual teacher, supplementing the teaching functions of human teachers and delivering information to students. In the second perspective, AI facilitated students in collecting information by enabling interactions with messages or peers. In the third perspective, the significance of the automatic evaluation function, which assessed learning activities and provided feedback to enhance the system while simultaneously implementing immediate changes in the learning process, was acknowledged. Regarding the role of communication, teachers clearly intended for students to acquire knowledge through it. Despite the focus on assisting individual learners, each article encompassed references from a wide range of fields and exhibited substantial diversity overall. Consequently, the domain of discussion forums with AI was depicted through the complex interplay between technology, pedagogy, and the learning environment. This context is known as entangled pedagogies, which emphasize understanding the interconnections among these elements and their reciprocal influences. In summary, AI was predominantly utilized in the form of chatbots and GenAI in discussion forums. Emerging AI roles included virtual teachers, peer/message matching, and automated evaluation. Aggregated information was presented in a manner that supported student learning. AI also served as a conduit between students and teachers.