Sentiment Analysis in Twitter Based on Knowledge Graph and Deep Learning Classification

被引:14
作者
Lovera, Fernando Andres [1 ]
Cardinale, Yudith Coromoto [1 ]
Homsi, Masun Nabhan [1 ,2 ]
机构
[1] Univ Simon Bolivar, Dept Comp Sci, Caracas 1080, Venezuela
[2] Helmholtz Dept Mol Syst Biol, Environm Res Ctr, D-04318 Leipzig, Germany
关键词
sentiment analysis; knowledge graph; Long-Short Term Memory (LSTM); model interpretability; SOCIAL MEDIA; WORDS; NETWORKS; MODEL; BAG;
D O I
10.3390/electronics10222739
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The traditional way to address the problem of sentiment classification is based on machine learning techniques; however, these models are not able to grasp all the richness of the text that comes from different social media, personal web pages, blogs, etc., ignoring the semantic of the text. Knowledge graphs give a way to extract structured knowledge from images and texts in order to facilitate their semantic analysis. This work proposes a new hybrid approach for Sentiment Analysis based on Knowledge Graphs and Deep Learning techniques to identify the sentiment polarity (positive or negative) in short documents, such as posts on Twitter. In this proposal, tweets are represented as graphs; then, graph similarity metrics and a Deep Learning classification algorithm are applied to produce sentiment predictions. This approach facilitates the traceability and interpretability of the classification results, thanks to the integration of the Local Interpretable Model-agnostic Explanations (LIME) model at the end of the pipeline. LIME allows raising trust in predictive models, since the model is not a black box anymore. Uncovering the black box allows understanding and interpreting how the network could distinguish between sentiment polarities. Each phase of the proposed approach conformed by pre-processing, graph construction, dimensionality reduction, graph similarity, sentiment prediction, and interpretability steps is described. The proposal is compared with character n-gram embeddings-based Deep Learning models to perform Sentiment Analysis. Results show that the proposal is able to outperforms classical n-gram models, with a recall up to 89% and F1-score of 88%.
引用
收藏
页数:18
相关论文
共 71 条
[11]  
Castillo E., 2015, P 9 INT WORKSH SEM E, P556
[12]  
Chagheri S, 2012, 2012 6TH INTERNATIONAL CONFERENCE ON SCIENCES OF ELECTRONICS, TECHNOLOGIES OF INFORMATION AND TELECOMMUNICATIONS (SETIT), P946, DOI 10.1109/SETIT.2012.6482041
[13]   Audio-Visual Sentiment Analysis for Learning Emotional Arcs in Movies [J].
Chu, Eric ;
Roy, Deb .
2017 17TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2017, :829-834
[14]  
Diaz-Rodriguez N., 2021, ARXIV210411914
[15]  
Dieber J., 2020, ARXIV201200093
[16]   Techniques for Interpretable Machine Learning [J].
Du, Mengnan ;
Li, Ninghao ;
Hu, Xia .
COMMUNICATIONS OF THE ACM, 2020, 63 (01) :68-77
[17]   Sentiment Analysis of Twitter Data [J].
El Rahman, Sahar A. ;
AlOtaibi, Feddah Alhumaidi ;
AlShehri, Wejdan Abdullah .
2019 INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCES (ICCIS), 2019, :336-339
[18]  
Falliat D, 2007, IEEE INT CONF ROBOT, P3921
[19]  
Fernando Sanchez-Rada J., 2014, Second International Workshop on Finance and Economics on the Semantic Web (FEOSW 2014), V1240, P51
[20]   Cross-domain polarity classification using a knowledge-enhanced meta-classifier [J].
Franco-Salvador, Marc ;
Cruz, Fermin L. ;
Troyano, Jose A. ;
Rosso, Paolo .
KNOWLEDGE-BASED SYSTEMS, 2015, 86 :46-56