Persian sentiment analysis of an online store independent of pre-processing using convolutional neural network with fastText embeddings

Shumaly, Sajjad; Yazdinejad, Mohsen; Guo, Yanhui

doi:10.7717/peerj-cs.422

Cited by 16 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…I. Aiming at this, an autonomous learning algorithm is adopted to combine the spatial and temporal feature information of the joints, which is called the spatial temporal graph convolution network (ST-GCN). In the ST-GCN algorithm, graph convolution is applied to the ST-GCN model to realize the description of the skeleton graph sequence ( 28 , 29 ). Figure 3 shows that each node corresponds to a joint point through the design of the skeleton diagram sequence.…”

Section: Research Methodology and Research Modelmentioning

confidence: 99%

Adoption of a deep learning-based neural network model in the psychological behavior analysis of resident tourism consumption

Huang

2022

Front. Public Health

View full text Add to dashboard Cite

With the development of society and the continuous progress of science and technology, it has become the mainstream measure to promote the development of the social economy through science and technology. Therefore, to improve the current situation of tourism consumption, improve the consumer sentiment of tourists, and promote the development of the tourism economy, the convolutional neural network (CNN) technology model is used to analyze the tourist's consumer psychology and behavior. Based on this, the user's consumption situation is analyzed, thus providing support for the intelligent improvement of tourism consumption. First, the basic characteristics of tourism consumption mood and behavior are introduced, and the methods to improve the tourism consumption mood and behavior are briefly introduced. Then, the CNN algorithm is employed to identify consumers' travel consumption behaviors and emotions. To improve the recognition effect, the algorithm is combined with skeleton node behavior recognition and video image behavior recognition. Finally, the performance of the designed algorithm is tested. The accuracy of the human behavior recognition (HBR) algorithm is more than 0.88. Compared with the detection effect of the HBR algorithm, the combined algorithm adopted in this work can reduce the image processing time and improve the detection efficiency. The multithread method can effectively reduce the complexity of the model and improve the recognition accuracy. The test results on different data sets show that the proposed algorithm can better adapt to the changes in identification samples and obtain more accurate recognition results compared with similar algorithms. In summary, this study not only provides technical support for the rational analysis of consumer sentiment and consumer behavior but also contributes to the comprehensive development of the tourism market.

show abstract

Section: Research Methodology and Research Modelmentioning

confidence: 99%

Adoption of a deep learning-based neural network model in the psychological behavior analysis of resident tourism consumption

Huang

2022

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…FastText is an open-source word embedding method developed by Facebook [10]. FastText has advantages in processing foreign languages because it can simplify language processing and reduce dependence on preprocessing data [10]. FastText categorizes each word into a series of vectors where each vector represents ngrams [11].…”

Section: Fasttext Feature Expansionmentioning

confidence: 99%

Aspect-Bas1ed Sentiment Analysis on Twitter Using Logistic Regression with FastText Feature Expansion

Alhakiem¹,

Setiawan²

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Social media has recently been widely used by users, especially Indonesians, as a place to express themselves in sentences, pictures, sounds, or videos. Twitter is one of the social media favored by people of diverse ages. Twitter is a social media that provides features like social media in general. However, Twitter has a unique feature where users can send or read text messages limited to only a few characters. Therefore, user tweets with topics related to a particular product can be utilized by companies to become input in the development of these products. This research was conducted using tweet data on the topic of Telkomsel, which is divided into two aspects, namely signal and service. Aspect-based sentiment analysis of Telkomsel was carried out using Logistic Regression with FastText feature expansion to reduce vocabulary mismatch in tweets so that the classification stage can be performed optimally. In addition, the Synthetic Minority Oversampling Technique (SMOTE) sampling method was applied to overcome data imbalance. The test results prove that feature expansion can improve F1-Score values for signal and service aspects. For the signal aspect, F1-Score increased by 3.33% from the baseline with a value of 96.48%. While for the service aspect, F1-Score increased by 12.91% from the baseline with a value of 95.57%.

show abstract

“…FastTextf model. The original word vector text matrix is averaged to obtain the hidden layer, and the Softmax layer in the model outputs the final classification prediction results ( Shumaly et al, 2021 ).…”

Section: Model Evaluation and Experimental Analysismentioning

confidence: 99%

Psychological Education Health Assessment Problems Based on Improved Constructive Neural Network

Fan

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

In order to better assess the mental health status, combining online text data and considering the problems of lexicon sparsity and small lexicon size in feature statistics of word frequency of the traditional linguistic inquiry and word count (LIWC) dictionary, and combining the advantages of constructive neural network (CNN) convolutional neural network in contextual semantic extraction, a CNN-based mental health assessment method is proposed and evaluated with the measurement indicators in CLPsych2017. The results showed that the results obtained from the mental health assessment by CNN were superior in all indicators, in which F1 = 0.51 and ACC = 0.69. Meanwhile, ACC evaluated by FastText, CNN, and CNN + Word2Vec were 0.66, 0.67, 0.67, and F1 were 0.37, 0.47, and 0.49, respectively, which indicates the use of CNN in mental health assessment has feasibility.

show abstract

Persian sentiment analysis of an online store independent of pre-processing using convolutional neural network with fastText embeddings

Cited by 16 publications

References 51 publications

Adoption of a deep learning-based neural network model in the psychological behavior analysis of resident tourism consumption

Adoption of a deep learning-based neural network model in the psychological behavior analysis of resident tourism consumption

Aspect-Bas1ed Sentiment Analysis on Twitter Using Logistic Regression with FastText Feature Expansion

Psychological Education Health Assessment Problems Based on Improved Constructive Neural Network

Contact Info

Product

Resources

About