Combining Sentiment-Combined Model with Pre-Trained BERT Models for Sentiment Analysis

A crucial task in sentiment analysis is aspect detection: the step of selecting the aspects on which opinions are expressed. This step anticipates the step of determining whether the opinions on aspects are positive or negative. This article proposes a novel probabilistic generative topic model for aspect-based sentiment analysis which is able to discover the latent structure of a large collection of review documents. The proposed joint sentiment-aspect detection model (SAM) is a generative topic model that incorporates the structure of review sentences for detecting aspects and sentiments simultaneously. The intuitions behind the SAM are that from generating documents by latent single- and multi-word topics, modelling the word distribution for each topic and learning of the prior distribution over topics in sentences of documents. SAM introduces word status so that the model can decide when to sample from a bigram distribution or a unigram distribution and integrates all these components into one combined model for aspect-based sentiment analysis. We evaluate SAM both qualitatively and quantitatively to show that the model is indeed able to perform the task effectively and improves significantly over standard joint sentiment-aspect models. The proposed model can easily be transformed between domains or languages and can detect the polarity of text data at various levels. However, for the quantitative analysis, we mainly focus on presenting the results for the document-level sentiment classification.

Download Full-text

An Application of the IFM Method for the Risk Assessment of Financial Instruments

Computational Economics ◽

10.1007/s10614-021-10208-4 ◽

2021 ◽

Author(s):

Adrià Pons ◽

Eduard Cristobal-Fransi ◽

Carla Vintrò ◽

Josep Rius ◽

Oriol Querol ◽

...

Keyword(s):

Risk Assessment ◽

Stock Market ◽

Sentiment Analysis ◽

Value At Risk ◽

Financial Instruments ◽

Combined Model ◽

Single Product ◽

Financial Firms ◽

Financial Products ◽

Future Work

AbstractExternal influences or behavioral biases can affect the way risk is perceived. This paper studies the prediction of VaR (Value at Risk) as a measure of the risk of loss for investments on financial products. Our aim is to predict the percentage of loss that a financial product would have in the future to assess the risks and determine the potential loss of a security in the stock market, thus reducing reasoning influenced by feelings for bank and financial firms seeking to deploy AI and advanced automation. We used the IFM (inference function for margins) method in different market scenarios, with particular emphasis on the strengths and weaknesses of it. The study is assessed on single product level with the skewed studen-t GARCH(1,1) model and portfolio level with t-copulas for the inter-dependencies. It has been shown that under normal market conditions the risk is predicted properly for both levels. However, when an unexpected market event occurs, the prediction fails. To address this limitation, a combined model with sentiment analysis and regression is proposed for further investigation as a future work.

Download Full-text

Performance Prediction of Asphalt Pavement Based on the Combined Model

CICTP 2020 ◽

10.1061/9780784483053.129 ◽

2020 ◽

Author(s):

Wenwen Feng ◽

Guanglai Jin ◽

Haiting Liu ◽

Zhixiang Zhang

Keyword(s):

Performance Prediction ◽

Asphalt Pavement ◽

Combined Model

Download Full-text

Study of Sentiment of Governor's Election Opinion in 2018

International Journal of Scientific Research in Science Engineering and Technology ◽

10.32628/ijsrset21841124 ◽

2018 ◽

pp. 231-238

Author(s):

Agung Eddy Suryo Saputro ◽

Khairil Anwar Notodiputro ◽

Indahwati A

Keyword(s):

Sentiment Analysis ◽

Naive Bayes ◽

Naïve Bayes ◽

Addition Method ◽

Sentiment Mining ◽

Positive Sentiment ◽

An historical analysis of species references in American English

Corpora ◽

10.3366/cor.2019.0177 ◽

2019 ◽

Vol 14 (3) ◽

pp. 327-349

Author(s):

Craig Frayne

Keyword(s):

Environmental Change ◽

Sentiment Analysis ◽

Quantitative Methods ◽

English Language ◽

Language Use ◽

American English ◽

Historical Analysis ◽

The Past ◽

Corpus Studies ◽

Google Books

This study uses the two largest available American English language corpora, Google Books and the Corpus of Historical American English (coha), to investigate relations between ecology and language. The paper introduces ecolinguistics as a promising theme for corpus research. While some previous ecolinguistic research has used corpus approaches, there is a case to be made for quantitative methods that draw on larger datasets. Building on other corpus studies that have made connections between language use and environmental change, this paper investigates whether linguistic references to other species have changed in the past two centuries and, if so, how. The methodology consists of two main parts: an examination of the frequency of common names of species followed by aspect-level sentiment analysis of concordance lines. Results point to both opportunities and challenges associated with applying corpus methods to ecolinguistc research.

Download Full-text