Sentiment analysis through recurrent variants latterly on convolutional neural network of Twitter

Abid, Fazeel; Alam, Muhammad; Yasir, Muhammad; Chen, Li

doi:10.1016/j.future.2018.12.018

Cited by 135 publications

(69 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…From among 32 of the analyzed studies, we identified three popular models for sentiment polarity analysis using deep learning: DNN [50], CNN [20], and hybrid [40]. In [13,18,46], three deep learning techniques, namely CNN, RNN, and LSTM, were individually tested on different datasets.…”

Section: Related Workmentioning

confidence: 99%

“…Several studies focus on building powerful models to solve the continuously increasing complexity of big data, as well as to expand sentiment analysis to a wide range of applications, from financial forecasting [5,6] and marketing strategies [7] to medicine analysis [8,9] and other areas [10][11][12][13][14][15][16][17][18]. However, few of them pay attention to evaluating different deep learning techniques in order to provide practical evidence of their performance [5,17,19,20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sentiment Analysis Based on Deep Learning: A Comparative Study

2020

View full text Add to dashboard Cite

The study of public opinion can provide us with valuable information. The analysis of sentiment on social networks, such as Twitter or Facebook, has become a powerful means of learning about the users' opinions and has a wide range of applications. However, the efficiency and accuracy of sentiment analysis is being hindered by the challenges encountered in natural language processing (NLP). In recent years, it has been demonstrated that deep learning models are a promising solution to the challenges of NLP. This paper reviews the latest studies that have employed deep learning to solve sentiment analysis problems, such as sentiment polarity. Models using term frequency-inverse document frequency (TF-IDF) and word embedding have been applied to a series of datasets. Finally, a comparative study has been conducted on the experimental results obtained for the different models and input features.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis Based on Deep Learning: A Comparative Study

2020

View full text Add to dashboard Cite

show abstract

“…Sentiment analysis, also known as opinion mining [16,17], is an important research topic in Natural Language Processing (NLP). Aspect-level sentiment classification is a fine-grained task in sentiment analysis.…”

Section: Aspect-level Sentiment Classificationmentioning

confidence: 99%

Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification

Zhao

Hou

2020

Knowledge-Based Systems

152

View full text Add to dashboard Cite

Aspect-level sentiment classification aims to distinguish the sentiment polarities over one or more aspect terms in a sentence. Existing approaches mostly model different aspects in one sentence independently, which ignore the sentiment dependencies between different aspects. However, we find such dependency information between different aspects can bring additional valuable information. In this paper, we propose a novel aspect-level sentiment classification model based on graph convolutional networks (GCN) which can effectively capture the sentiment dependencies between multi-aspects in one sentence. Our model firstly introduces bidirectional attention mechanism with position encoding to model aspect-specific representations between each aspect and its context words, then employs GCN over the attention mechanism to capture the sentiment dependencies between different aspects in one sentence. We evaluate the proposed approach on the SemEval 2014 datasets. Experiments show that our model outperforms the state-of-the-art methods. We also conduct experiments to evaluate the effectiveness of GCN module, which indicates that the dependencies between different aspects is highly helpful in aspect-level sentiment classification.

show abstract

“…The sentiment analysis has mainly three categories (i) Positive, (ii) Negative and (iii) Neutral [1] [13] .The results are finally analyzed and the sentiment score is generated.16 types of personality traits are pre-defined. The replies of the users are passed to a RNN .The traits are classified by the network.…”

Section: Introductionmentioning

confidence: 99%

Chatbot for Monitoring Mental Health and Personality Trait Identification

Jeba¹,

Bharath²,

Gowtam³

et al. 2019

IJITEE

View full text Add to dashboard Cite

AI Chabot or conversational agents are application that mimics human communication. They can entertain, motivate and actively engage people. An important concern faced by most people is stressed disorders. These disorders can include OCD and posttraumatic stress disorders. Most affected category of people is the employees and students. In order to prevent this, counseling is provided. It is done by the HR managers in IT companies and by the teachers to the students or by professionals. But most people are not open to the specialists and feel more uncomfortable during this process of expressing their feelings. This process can be made simple by using a Chatbot. This Chatbot communicates with the people, identifies their traits and provides their sentiment scores to an authorized person. There are three key modules in the development process. First is the Sequence-to-Sequence model. This model consists of an encoder and a decoder. The received input text is converted to tokens and each token is identified with a random number, which is common for the same tokens. The second module is the sentiment analysis which is used in identifying the emotions of a person. The sentiment score is generated for the users. The traits of the person are identified from the chat logs. A RNN (Recurrent Neural Network) is built to identify the trait of the person from the pre-defined 16 types of personality traits. The multi-class classifier’s output can be combined with the sentiment score to truly identify the characteristics of the users.

show abstract

Sentiment analysis through recurrent variants latterly on convolutional neural network of Twitter

Cited by 135 publications

References 16 publications

Sentiment Analysis Based on Deep Learning: A Comparative Study

Sentiment Analysis Based on Deep Learning: A Comparative Study

Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification

Chatbot for Monitoring Mental Health and Personality Trait Identification

Contact Info

Product

Resources

About