NEUROSENT-PDI at SemEval-2018 Task 1: Leveraging a Multi-Domain Sentiment Model for Inferring Polarity in Micro-blog Text

作者: Mauro Dragoni

DOI: 10.18653/V1/S18-1013

关键词:

摘要: This paper describes the NeuroSent system that participated in SemEval 2018 Task 1. Our takes a supervised approach builds on neural networks and word embeddings. Word embeddings were built by starting from repository of user generated reviews. Thus, they are specific for sentiment analysis tasks. Then, tweets converted corresponding vector representation given as input to network with aim learning different semantics contained each emotion taken into account task. The output layer has been adapted based characteristics subtask. Preliminary results obtained provided training set encouraging pursuing investigation this direction.

参考文章(23)
T. Yamada, K. Ueda, Explanation of binarized time series using genetic learning model of investor sentiment congress on evolutionary computation. ,vol. 3, pp. 2437- 2444 ,(2005) , 10.1109/CEC.2005.1554999
An-Pin Chen, Yung-Hua Chang, Using Extended Classifier System to Forecast SaP Futures Based on Contrary Sentiment Indicators congress on evolutionary computation. ,vol. 3, pp. 2084- 2090 ,(2005) , 10.1109/CEC.2005.1554952
Mauro Dragoni, Andrea G. B. Tettamanzi, Célia da Costa Pereira, Propagating and Aggregating Fuzzy Polarities for Concept-Level Sentiment Analysis Cognitive Computation. ,vol. 7, pp. 186- 197 ,(2015) , 10.1007/S12559-014-9308-6
Angela Charng-Rurng Tsai, Chi-En Wu, Richard Tzong-Han Tsai, Jane Yung-jen Hsu, Building a Concept-Level Sentiment Dictionary Based on Commonsense Knowledge IEEE Intelligent Systems. ,vol. 28, pp. 22- 30 ,(2013) , 10.1109/MIS.2013.25
Rui Xia, Chengqing Zong, Xuelei Hu, Erik Cambria, Feature Ensemble Plus Sample Selection: Domain Adaptation for Sentiment Classification IEEE Intelligent Systems. ,vol. 28, pp. 10- 18 ,(2013) , 10.1109/MIS.2013.27
Danushka Bollegala, David Weir, John Carroll, Cross-Domain Sentiment Classification Using a Sentiment Sensitive Thesaurus IEEE Transactions on Knowledge and Data Engineering. ,vol. 25, pp. 1719- 1731 ,(2013) , 10.1109/TKDE.2012.103
Sinno Jialin Pan, Xiaochuan Ni, Jian-Tao Sun, Qiang Yang, Zheng Chen, Cross-domain sentiment classification via spectral feature alignment the web conference. pp. 751- 760 ,(2010) , 10.1145/1772690.1772767
Chih-Chung Chang, Chih-Jen Lin, LIBSVM ACM Transactions on Intelligent Systems and Technology. ,vol. 2, pp. 1- 27 ,(2011) , 10.1145/1961189.1961199
Mark Dredze, John Blitzer, Fernando Pereira, Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification meeting of the association for computational linguistics. pp. 440- 447 ,(2007)
Giulio Petrucci, Mauro Dragoni, An Information Retrieval-Based System for Multi-domain Sentiment Analysis Semantic Web Evaluation Challenges. pp. 234- 243 ,(2015) , 10.1007/978-3-319-25518-7_20