Sentiment Analysis Using AI: A Comparative Study Comparative Study of 5 Different Algorithms and Benchmarking Them with A Qualitative Analysis of Training time, Prediction time, and Accuracy

2021 ◽  
Author(s):  
Jeet Biswas ◽  
Markus Haid ◽  
Ishak Boyaci ◽  
Indrashis Nath ◽  
Bharat Hegde ◽  
...  
Keyword(s):  
Comparative Study ◽  
Qualitative Analysis ◽  
Sentiment Analysis ◽  
Training Time ◽  
Time Prediction ◽  
Prediction Time

scholarly journals Newspaper Article Classification using Machine Learning Techniques

2020 ◽  
Vol 9 (5) ◽  
pp. 872-877
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Machine Learning Techniques ◽  
Learning Approach ◽  
Training Time ◽  
Time Prediction ◽  
Learning Techniques ◽  
Prediction Time ◽  
Newspaper Articles

Newspaper articles offer us insights on several news. They can be one of many categories like sports, politics, Science and Technology etc. Text classification is a need of the day as large uncategorized data is the problem everywhere. Through this study, We intend to compare several algorithms along with data preprocessing approaches to classify the newspaper articles into their respective categories. Convolutional Neural Networks(CNN) is a deep learning approach which is currently a strong competitor to other classification algorithms like SVM, Naive Bayes and KNN. We hence intend to implement Convolutional Neural Networks - a deep learning approach to classify our newspaper articles, develop an understanding of all the algorithms implemented and compare their results. We also attempt to compare the training time, prediction time and accuracies of all the algorithms.

A Survey and Comparative Study of Tweet Sentiment Analysis via Semi-Supervised Learning

2016 ◽  
Vol 49 (1) ◽  
pp. 1-26 ◽  
Author(s):  
Nadia Felix F. Da Silva ◽  
Luiz F. S. Coletta ◽  
Eduardo R. Hruschka
Keyword(s):  
Comparative Study ◽  
Sentiment Analysis ◽  
Supervised Learning

What do children say about tidy-up time? A comparative study of American and Taiwanese children’s perceptions of tidy-up time

2017 ◽  
Vol 12 (4) ◽  
pp. 452-460
Author(s):  
Satomi Izumi-Taylor ◽  
Chia-Hui Lin
Keyword(s):  
Comparative Study ◽  
Qualitative Analysis ◽  
Children’S Perspectives ◽  
Children's Perceptions ◽  
Children’S Perceptions ◽  
Southeastern Us ◽  
Similarities And Differences ◽  
Central Taiwan ◽  
Safe Environments

The purpose of this study was to examine the similarities and differences in American and Taiwanese children’s perspectives of tidy-up time. The participants consisted of 25 American kindergarteners in the southeastern US, and 25 Taiwanese kindergarteners from central Taiwan. Children were asked to respond to five questions regarding tidy-up time. Qualitative analysis of the data yielded four themes: transitions, clean and safe environments, work, and cooperation. All participants associated tidy-up time with transitions. They considered tidy-up as the notion of maintaining clean environments, but only Taiwanese children perceived it to be keeping the classroom safe. Also, all participants viewed such time as work, and as time to cooperate with each other. More Taiwanese children’s responses indicated how they and their teachers cooperate during cleaning as compared to their American counterparts.

scholarly journals Sentiment Analysis Method of Network Text Based on Improved AT-BiGRU Model

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xinxin Lu ◽  
Hong Zhang
Keyword(s):  
Sentiment Analysis ◽  
Current Method ◽  
Recurrent Network ◽  
Analysis Method ◽  
Large Space ◽  
Spelling Errors ◽  
Training Time ◽  
Proposed Model ◽  
Correct Spelling ◽  
Text Sentiment Analysis

In order to solve the problems existing in the current method of emotional analysis of network text, such as long training time, complex calculation, and large space cost, this paper proposes an Internet text sentiment analysis method based on the improved AT-BiGRU model. Firstly, the textblob package is imported to correct spelling errors before text preprocessing. Secondly, pad_sequences are used to fill in the input layer with a fixed length, the two-way gated recurrent network is used to extract information, and the attention mechanism is used to highlight the key information of the word vector. Finally, the GNU memory unit is transformed, and an improved BiGRU that can adapt to the recursive network structure is constructed. The proposed model is experimentally demonstrated on the SemEval-2014 Task 4 and SemEval-2017 Task 4 datasets. Experimental results show that the proposed model can effectively avoid the text sentiment analysis bias caused by spelling errors and prove the effectiveness of the improved AT-BiGRU model in terms of accuracy, loss rate, and iteration time.

Predicting Outcomes of Business Process Executions Based on LSTM Neural Networks and Attention Mechanism

2021 ◽  
Author(s):  
Jiaojiao Wang ◽  
Dongjin Yu ◽  
Chengfei Liu ◽  
Xiaoxiao Sun
Keyword(s):  
Short Term Memory ◽  
Attention Mechanism ◽  
Sequential Data ◽  
Time Prediction ◽  
Prediction Time ◽  
Highly Sensitive ◽  
Long Short Term Memory ◽  
Early Decision ◽  
Lstm Network ◽  
Hidden Layer

Abstract To effectively predict the outcome of an on-going process instance helps make an early decision, which plays an important role in so-called predictive process monitoring. Existing methods in this field are tailor-made for some empirical operations such as the prefix extraction, clustering, and encoding, leading that their relative accuracy is highly sensitive to the dataset. Moreover, they have limitations in real-time prediction applications due to the lengthy prediction time. Since Long Short-term Memory (LSTM) neural network provides a high precision in the prediction of sequential data in several areas, this paper investigates LSTM and its enhancements and proposes three different approaches to build more effective and efficient models for outcome prediction. The first move on enhancement is that we combine the original LSTM network from two directions, forward and backward, to capture more features from the completed cases. The second move on enhancement is that we add attention mechanism after extracting features in the hidden layer of LSTM network to distinct them from their attention weight. A series of extensive experiments are evaluated on twelve real datasets when comparing with other approaches. The results show that our approaches outperform the state-of-the-art ones in terms of prediction effectiveness and time performance.

Sign in / Sign up

Export Citation Format

Share Document