Name
Title | ||
|---|---|---|
WRS: A Novel Word-embedding Method for Real-time Sentiment with Integrated LSTM-CNN Model |
Abstract | ||
|---|---|---|
Artificial Intelligence (AI) is a research-focused technology in which Natural Language Processing (NLP) is a core technology in AI. Sentiment Analysis (SA) aims to extract and classify the people's opinions by NLP. The Machine Learning (ML) and lexicon dictionaries have limited competency to efficiently analyze massive live media data. Recently, deep learning methods significantly enrich the accuracy of recent sentiment models. However, the existing methods provide the aspect-based extraction that reduces individual word accuracy if a sentence does not follow the aspect information in real-time. Therefore, this paper proposes a novel word embedding method for the real-time sentiment (WRS) for word representation. The WRS's novelty is a novel word embedding method, namely, Word-to-Word Graph (W2WG) embedding that utilizes the Word2Vec approach. The WRS method assembles the different lexicon resources to employ the W2WG embedding method to achieve the word feature vector. Robust neural networks leverage these features by integrating LSTM and CNN to improve sentiment classification performance. LSTM is utilized to store the word sequence information for the effective real-time SA, and CNN is applied to extract the leading text features for sentiment classification. The experiments are conducted on Twitter and IMDB datasets. The results demonstrate our proposed method's effectiveness for real-time sentiment classification. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/RCAR52367.2021.9517671 | 2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) |
Keywords | DocType | ISBN |
deep learning methods,recent sentiment models,aspect-based extraction,individual word accuracy,word embedding method,word representation,WRS's novelty,Word-to-Word Graph,Word2Vec approach,WRS method,W2WG embedding method,word feature vector,sentiment classification performance,word sequence information,real-time sentiment classification,novel Word-embedding method,integrated LSTM-CNN model,AI,research-focused technology,Natural Language Processing,NLP,Sentiment Analysis,lexicon dictionaries,massive live media data | Conference | 978-1-6654-3679-3 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Abdur Rasool | 1 | 0 | 0.34 |
| Qingshan Jiang | 2 | 0 | 0.34 |
| qiang qu | 3 | 83 | 12.15 |
| Chaojie Ji | 4 | 0 | 0.34 |