Naive bayes algorithm performance for smartphone sentiment analysis in social media

Integrating color cues to improve multimodal sentiment analysis in social media

Research on Sentiment Analysis in social media by using Mesopotamian-Iraqi Dialect (MID) of Arabic language was rarely found, there is no reliable dataset developed in MID neither an annotated corpus for the sentiment analysis of social media in this dialect. Therefore, this gap was the main stumbling block for researchers of sentiment analysis in MID, for this reason, this paper introduced the development of an annotated corpus of Mesopotamian-Iraqi Dialect for sentiment analysis in social media and named it as (ACMID) stands for (the annotated corpus of Mesopotamian-Iraqi Dialect) to help researchers in future for using this corpus for their studies, to the best of our knowledge this is the first annotated corpus that both classify polarity as well as emotion classification in MID. Likewise, Facebook as the most popular social platform among Iraqis was used to extract the data from its popular Iraqi pages. 5000 comments were extracted from these pages classified by its polarity (Positive, Negative, Neutral, Spam) by two Iraqi annotators, these annotators were simultaneously classifying the same comments according to Ekman seven universal emotions (Anger, Fear, Disgust, Happiness, Sadness, Surprise, Contempt) or no emotion. Cohen's kappa coefficient was then used to compare the two annotators’ results to find the reliability of these results. The data shows a comparable value among the two annotators for the polarity classification as high as 0.82, while for the emotion classification the result was 0.65.

Sentiment Analysis in Social Media and Its Application: Systematic Literature Review

This research aims to present a bibliometric review of sentiment analysis in social media, highlighting its evolution, key contributors, and emerging themes. The study utilizes the Clarivate Web of Science database, employing a strategic search methodology to ensure accurate results. With the assistance of RStudio and the “bibliometrix” package, the research employs a rigorous approach to analyse 764 articles, emphasizing themes, citation patterns, and collaborative dynamics. Research output from 2011 to 2023 revealed significant growth in the sentiment analysis domain, with an annual growth rate of nearly 40%. The collaborative nature of this domain is evident, with international collaborations constituting 27%. Geographically, the USA, China, and India dominate, though there is significant input from multiple countries worldwide. This bibliometric review is a comprehensive exploration of sentiment analysis in social media, presenting insights into the field’s progression, interdisciplinary nature, and potential future trajectories. It underscores the importance of international collaborations and quality-driven research, suggesting avenues for future exploration in the dynamic landscape of digital communication.

Statements issued by public officials will be pros and cons in the community, there are those who respond positively, negatively or respond neutrally. Likewise on Instagram social media, every statement written on Instagram will get various responses written by netizens in the comment’s column posted. Netizen is an acronym for internet citizens, namely people who are actively using the internet. Due to the large number of comments, it is difficult to see whether the public response is a positive, negative or neutral comment when responding to statements from public officials. Whether the statements issued by public officials through Instagram have a positive, negative or neutral impact, so that if they can be grouped into labels, it can be seen how much public opinion is against these public figures. On social media accounts, not all comments written by netizens have the same writing structure, so we need a mechanism that is able to help analyze comments from netizens by classifying them into positive, negative or neutral response classes. By applying POS Tagging to determine opinion sentences or not and also the Naïve Bayes Classifier method and the tf-idf feature to be able to classify comments into several classes of positive, negative or neutral comments. The classification testing stage uses the cross validation method to test the accuracy of the naive bayes classification algorithm and the tf-idf feature.

ABSTRACTTraditional sentiment analysis methods do not perform well when applied to social media data. In this study, we propose an approach to improve sentiment analysis performance in the context of social media. Our approach utilizes three types of additional information that can be collected from social media platforms—personal preference, friend influence, and herding effect—to enrich the input features of a supervised sentiment classification model. We implement the approach on data sets collected from Twitter across two industries (airlines and wireless service providers) and present the performance improvement attained by combining social features with pure text‐based features. To further investigate the operational implications of this improvement, we develop a stylized service recovery model for customer relationship management in social media. Our work has implications for automating social media monitoring and, more broadly, for improving customer relationship management in organizations.

Social media has become a one-stop shop for consuming news and expressing political views. Politics has become increasingly emotional, and the ensuing polarization has created echo chambers that favor narratives and stories that repeat only one point of view. In this article, we investigated the role of political activity through Twitter (now ‘X’) engagement as a predictor of destructive fires and deforestation in the Brazilian Legal Amazon (BLA). We used a machine learning approach based on sentiment analysis and satellite data. To test the consistency of the sentiment analysis, we compared the timing of messages related to fire and deforestation events with daily fire data from satellites. When comparing positive and negative comments about fires in the BLA, the results showed that the best model for predicting fire outbreaks is the decision tree regressor. We found evidence that positive comments about agriculture, industry, and the Amazon rainforest in response to speeches and statements by high-ranking Brazilian politicians tend to induce positive comments about fire outbreaks and deforestation. These comments then become good predictors of fire outbreaks with a 6-day lag. These results support the view that high-ranking politicians have enormous power to influence damaging events that can have severe impacts on communities, the environment, and the economy. Brazil has seen an unprecedented increase in deforestation and fires in the Amazon rainforest in recent years. Our findings contribute to the growing literature on the role of social media in real-world events and how machine learning approaches can be used to address this class of problems.

Education sector has witnessed several changes in the recent past. These changes have forced private universities into fierce competition with each other to get more students enrolled. This competition has resulted in the adoption of marketing practices by private universities similar to commercial brands. To get competitive gain, universities must observe and examine the students' feedback on their own social media sites along with the social media sites of their competitors. This study presents a novel framework which integrates numerous analytical approaches including statistical analysis, sentiment analysis, and text mining to accomplish a competitive analysis of social media sites of the universities. These techniques enable local universities to utilize social media for the identification of the most-discussed topics by students as well as based on the most unfavorable comments received, major areas for improvement. A comprehensive case study was conducted utilizing the proposed framework for competitive analysis of few top ranked international universities as well as local private universities in Lahore Pakistan. Experimental results show that diversity of shared content, frequency of posts, and schedule of updates, are the key areas for improvement for the local universities. Based on the competitive intelligence gained several recommendations are included in this paper that would enable local universities generally and Riphah international university (RIU) Lahore specifically to promote their brand and increase their attractiveness for potential students using social media and launch successful marketing campaigns targeting a large number of audiences at significantly reduced cost resulting in an increased number of enrolments.

Many online platforms for movie streaming have emerged nowadays in Indonesia with the development of technology. Streaming platforms that are widely used by the public are Netflix, Disney+, HBO Go, WeTV, Vidio. A lot of comparisons between streaming platforms have become a topic of discussion on social media. The opinions expressed by users of the streaming platform greatly affect other users who want to watch the movie. The transmission of opinions from users becomes positive and negative comments that are received by the public and spread widely on social media. Opinions that contain both positive and negative comments become a problem and can affect other users who want to watch movies through streaming platforms. The opinions of users about the streaming platform can be analyzed through sentiment analysis. At the stage of data collection using scrapy framework tools with Python, as much as 1,500 lines of text are preprocessed. LDA method to present topics that contain representative words. Classification using the Support Vector Machine (SVM) gets more positive comments than negative comments. The test results obtained an accuracy of 0.82, recall of 0.8, F1 score of 0.79, and precision of 0.8.

User-generated content in social media contain very meaningful information about public sentiment and stance and require automated methods to analyze them extract knowledge from them. The recognition of sentiments, emotions and attitudes in textual data is necessary for understanding public stance and is highly desired for various services and procedures. In this work, we examine the performance of Hidden Markov Models (HMM) in the recognition of sentiments and opinions in text. Hidden Markov Models constitute a quite suitable approach given the special characteristics of the textual data. In particular, they can utilize the sequential nature of textual data, a piece of information that traditional machine learning approaches fail to fully take into account. We performed several experiments in order to assess the performance of different HMM-based methods under various training parameters and architectures. The evaluation results indicate that Hidden Markov Models achieve superior performance compared to traditional machine learning algorithms and highlight that they are scalable and accurate in analyzing user generated content and in specifying opinions and attitudes.

One of the ways to control the spread of COVID-19 is vaccination. However, discussions about the effectiveness of vaccines are still visible, especially in various social media. Not yet finished about this, now a new variant of covid 19 has emerged, namely Omicron. The news through the youtube channel is also sought after and seen by people to find out what this omicron virus looks like and the effectiveness of the vaccine that has been carried out by the community against this new virus. In this study, the detection of public opinion about the effectiveness of vaccination using the Support Vector Machine algorithm. The dataset was taken by crawling the YouTube comments of English news channels and then labeling lexicon-based comments using TextBlob and VADER into positive, negative, and neutral comments. There are differences in the number of positive, negative, and neutral comments with the two text labeling methods, but not too far. The application of the SVM algorithm to the dataset with the comment labeling of the TextBlob method resulted in an accuracy of 63%, while the application of the SVM with the comment labeling of the VADER method resulted in an accuracy of 70%.

Sentiment analysis in social media has grabbed more considerable attention because the results of such studies are highly applicable in social, economic, and political contexts. This study aimed to present an approach for collecting data from Twitter while storing and analysing the data using the hadoop as a big data platform as well as a hybrid trial and error model using the Bayes theorem plus a dictionary of words for the sentiment analysis. This method classifies tweets in two positive and negative classes based on the probability of positive words and negative words. According to the results, the accuracy of the proposed approach boosted from 67% to 71%. Then a new idea was employed in form of a weighted dictionary to achieve a higher accuracy. As such. the accuracy of the proposed approach reached a rate of 78% according to the results of another analysis conducted on the same data.

Sentiment Analysis deals with the detection and analysis of affective content in written text. It utilizes methodologies, theories, and techniques from a diverse set of scientific domains, ranging from psychology and sociology to natural language processing and machine learning. In this chapter, we discuss the contributions of the field in social media analysis with a particular focus in online collective actions; as these actions are typically motivated and driven by intense emotional states (e.g., anger), sentiment analysis can provide unique insights into the inner workings of such phenomena throughout their life cycle. We also present the state of the art in the field and describe some of its contributions into understanding online collective behavior. Lastly, we discuss significant real-world datasets that have been successfully utilized in research and are available for scientific purposes and also present a diverse set of available tools for conducting sentiment analysis.

This chapter delves into the history and current status of sentiment analysis, focusing on its application in the context of Indonesian small and medium-sized enterprises (SMEs). By analyzing the utilization of sentiment analysis in social media, particularly its impact on Indonesian SMEs, this chapter aims to shed light on the possibilities and potential benefits of integrating sentiment analysis tools into the business strategies of these enterprises.

Multimodal sentiment analysis faces a number of challenges, including modality missing, modality heterogeneity gap, incomplete datasets, etc. Previous studies usually adopt schemes like meta-learning or multi-layer structures. Nevertheless, these methods lack interpretability for the interaction between modalities. In this paper, we constructed a new dataset, SM-MSD, for sentiment analysis in social media (SAS) that differs significantly from conventional corpora, comprising 10K instances of diverse data from Twitter, encompassing text, emoticons, emojis, and text embedded in images. This dataset aims to reflect authentic social scenarios and various emotional expressions, and provides a meaningful and challenging evaluation benchmark for multimodal sentiment analysis in specific contexts. Furthermore, we propose a multi-task framework based on heterogeneous graph neural networks (H-GNNs) and contrastive learning. For the first time, heterogeneous graph neural networks are applied to multimodal sentiment analysis tasks. In the case of additional labeling data, it guides the emotion prediction of the missing mode. We conduct extensive experiments on multiple datasets to verify the effectiveness of the proposed scheme. Experimental results demonstrate that our proposed scheme surpasses state-of-the-art methods by 1.7% and 0 in accuracy and 1.54% and 4.9% in F1-score on the MOSI and MOSEI datasets, respectively, and exhibits robustness to modality missing scenarios.