China
Africa
Explore chapters and articles related to this topic
Cross-Domain Analysis of Social Data and the Effect of Valence Shifters
Published in Balwinder Raj, Brij B. Gupta, Jeetendra Singh, Advanced Circuits and Systems for Healthcare and Security Applications, 2023
In 2008, Bo Pang [13] discussed the concept on opinion and sentiment analysis in detail, concentrating on difficulties and challenges in this field. In 2010, Hsinchun Chen [14] also discussed the past implementations and techniques. He concluded that high perfection levels in sentiment analysis are not reached yet because enough work has not been done on this topic. Anuj Sharma [15] compared different machine learning and feature extraction techniques and came to the conclusion that SVM performs best in machine learning and Naïve-Bayesian as the best classifier. Dhiraj [16] used a feature vector of test data to create an automated program for sentiment analysis of social data. In the year 2014, a survey was again done in sentiment analysis. Walla [17] made a survey from very initial level and concluded that Naïve-Bayesian and SVM are the most frequently used in sentiment analysis. One of the major challenges in sentiment analysis are that most of the techniques do not work on multiple languages. Fotis Asiopos [18] tried to make a technique that could work for multiple languages on social data.
Analytics of IoT, SAR, and Social Network Data for Detection of Anomalies in Climate Conditions
Published in Monika Mangla, Ashok Kumar, Vaishali Mehta, Megha Bhushan, Sachi Nandan Mohanty, Real-Life Applications of the Internet of Things, 2022
People are also sharing the critical information related to natural disasters, extreme conditions or such related events are social media, though the authenticity is questionable semantic data analytics tools can be used on the data collected from various users for understanding the nature of the situation through natural language processing (NLP) [6]. Sentiment analysis comes under a special category of data mining that evaluates the disposition of people’s opinions using NLP, text analysis, and last but not the least computational linguistics, which are then used to analyze and extract subjective information from social media and similar sources through the internet. The insight after data analytics quantifies the general public’s sentiments or responses toward specific people, ideas, products, or events and reveal the information’s contextual polarity. Opinion mining is another name of sentiment analysis [6].
Deep Neural Networks (DNNs) for Virtual Assistant Robots
Published in Mehdi Ghayoumi, Deep Learning in Practice, 2021
There are many applications for sentiment analysis. For example, suppose a company created a product, and they would like to know about the user feedback to improve their product. One of the methods is to check customer feedback through social media comments like Twitter and Facebook. For example, if there are thousands of words on customer feedback, doing sentiment analysis helps get a general opinion about the positive or negative of a product. For doing sentiment analysis, you should know about text processing. Text is another type of data (that is the output here). In this step, we use these text data (extracted in the previous step) to do some sentiment analysis to decide or generate a report. You should know two definitions: a) bag of the word: it is a sequence of the word and b) word embedding: it is the process of converting word to vector. If you have a bag of words, using some methods like MLP is not good for this purpose. You can use a deep neural network to convert a sequence of the words to a vector (encoding) and then convert the vector to a sequence of the desired format (decoding). After converting each word to a vector, there is a matrix (each row in this matrix is a vector that represents a word) for a set of the word. Now the algorithm finds the probability of the word's occurrence and the words around this word. Then by using SoftMax, it converts each word value and probabilities to one probability. Each word in the same context has a similar vector. For example, the words kitchen and oven are similar in comparison to kitchen and history.
Deep Sentiments Analysis for Roman Urdu Dataset Using Faster Recurrent Convolutional Neural Network Model
Published in Applied Artificial Intelligence, 2022
Arfan Ali Nagra, Khalid Alissa, Taher M. Ghazal, Saigeeta Kukunuru, Muhammad Mugees Asif, Muhammad Fawad
As technology expands rapidly in the recent years, now every individual is using internet which provide the most significant way for e-shopping, e-learning, telemedicine and provide a social platform for communication and interactions between different people by using different social networking sites like Facebook, Twitter, Instagram, Blogs and many other that allow people to engage in discussion group and express their opinions with anonymity (Al-Smadi et al. 2019; Lytos et al. 2019; Vuong et al. 2019). While dealing with social media, sentiment analysis is the most important task to understand the behavior and attitude of an individual toward a particular problem and get to know what the people actually think (Sailunaz and Alhajj 2019). Sentiment analysis analyze the emotions of the users behind text written by the user by using different machine learning technique like Natural Language Processing (NLP), text analytics, computational linguistics, and so on (Ananiadou, Thompson, and Nawaz 2013; Xing, Pallucchini, and Cambria 2019).
The influence of psychological language words contained in microblogs on dissemination behaviour in emergency situations – mediating effects of emotional responses
Published in Behaviour & Information Technology, 2022
Yanxia Lu, Jiangnan Qiu, Chun Jin, Wenjing Gu, Shangxiao Dou
Sentiment analysis is the computational study of people’s opinions, attitudes, and emotions to individuals, events, or topics in which the sentiments expressed in the text are identified and analysed. Sentiment analysis may be considered a classification process (Medhat, Hassan, and Korashy 2014) in which emotions expressed in the text are generally divided into positive, negative, and neutral emotions. Emotions can also be more specifically categorised. Given the limitations contained in negative, ironic, metaphorical, and other words, sentiment analysis techniques are not always accurate for analyzing the emotions contained in microblog text. Some psychologists believe that sentiment analysis is how engineers think emotions work. Putting emotional experiences into words changes the way events are organised in the brain. To understand how people express their emotions, a dictionary of emotional words is considered important (Pennebaker 2017).
Prediction of user loyalty in mobile applications using deep contextualized word representations
Published in Journal of Information and Telecommunication, 2022
As a natural language processing technique, sentiment analysis allows the identification and categorizations of emotions expressed in a piece of text. Sentiment analysis is widely applied to user reviews and surveys expressed in the text to extract opinions or sentiments of users about a product or service. Application stores such as Google Play, Apple AppStore provide user ratings and reviews about mobile applications. In our previous paper (Kilimci et al., 2020), we presented sentiment analysis-based churn prediction in mobile games using word embedding models and deep learning algorithms. The aim of this paper is to apply sentiment analysis methods for the estimation of user loyalty on data collected from the application store’s ratings and reviews. Datasets are represented by using Word2Vec, Glove, and FastText word embedding models. Three deep learning algorithms and four deep contextualized word representations are employed for the loyalty prediction. While Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and Long Short-Term Memory (LSTMs) are used as deep learning algorithms, bidirectional encoder representations from transformers (BERT), Multilingual BERT (MBERT), DistilBERT (DBERT), Robustly Optimized BERT (RoBERTa) are employed as deep contextualized word representations in this work.