Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Sentiment": models, code, and papers

Exploiting Position Bias for Robust Aspect Sentiment Classification

May 29, 2021
Fang Ma, Chen Zhang, Dawei Song

Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence. While state-of-the-art ASC models have achieved remarkable performance, they are recently shown to suffer from the issue of robustness. Particularly in two common scenarios: when domains of test and training data are different (out-of-domain scenario) or test data is adversarially perturbed (adversarial scenario), ASC models may attend to irrelevant words and neglect opinion expressions that truly describe diverse aspects. To tackle the challenge, in this paper, we hypothesize that position bias (i.e., the words closer to a concerning aspect would carry a higher degree of importance) is crucial for building more robust ASC models by reducing the probability of mis-attending. Accordingly, we propose two mechanisms for capturing position bias, namely position-biased weight and position-biased dropout, which can be flexibly injected into existing models to enhance representations for classification. Experiments conducted on out-of-domain and adversarial datasets demonstrate that our proposed approaches largely improve the robustness and effectiveness of current models.

* 7 pages, 2 figures, 4 tables, accepted to Findings of ACL 2021. Repo: 

  Access Paper or Ask Questions

Aspect-based Sentiment Analysis in Document - FOMC Meeting Minutes on Economic Projection

Aug 09, 2021

The Federal Open Market Committee within the Federal Reserve System is responsible for managing inflation, maximizing employment, and stabilizing interest rates. Meeting minutes play an important role for market movements because they provide the birds eye view of how this economic complexity is constantly re-weighed. Therefore, There has been growing interest in analyzing and extracting sentiments on various aspects from large financial texts for economic projection. However, Aspect-based Sentiment Analysis is not widely used on financial data due to the lack of large labeled dataset. In this paper, I propose a model to train ABSA on financial documents under weak supervision and analyze its predictive power on various macroeconomic indicators.

  Access Paper or Ask Questions

When and Why does a Model Fail? A Human-in-the-loop Error Detection Framework for Sentiment Analysis

Jun 02, 2021
Zhe Liu, Yufan Guo, Jalal Mahmud

Although deep neural networks have been widely employed and proven effective in sentiment analysis tasks, it remains challenging for model developers to assess their models for erroneous predictions that might exist prior to deployment. Once deployed, emergent errors can be hard to identify in prediction run-time and impossible to trace back to their sources. To address such gaps, in this paper we propose an error detection framework for sentiment analysis based on explainable features. We perform global-level feature validation with human-in-the-loop assessment, followed by an integration of global and local-level feature contribution analysis. Experimental results show that, given limited human-in-the-loop intervention, our method is able to identify erroneous model predictions on unseen data with high precision.

* NAACL2021 

  Access Paper or Ask Questions

Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis

Sep 18, 2019
Minlong Peng, Qi Zhang, Xuanjing Huang

Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may harm domain adaptation when the label distribution $\rm{P}(\rm{Y})$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing SOTA DIRL models to WDIRL. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution.

* Address the problem of the domain-invariant representation learning framework under target shift 

  Access Paper or Ask Questions

An Empirical Study on Sentiment Classification of Chinese Review using Word Embedding

Nov 05, 2015
Yiou Lin, Hang Lei, Jia Wu, Xiaoyu Li

In this article, how word embeddings can be used as features in Chinese sentiment classification is presented. Firstly, a Chinese opinion corpus is built with a million comments from hotel review websites. Then the word embeddings which represent each comment are used as input in different machine learning methods for sentiment classification, including SVM, Logistic Regression, Convolutional Neural Network (CNN) and ensemble methods. These methods get better performance compared with N-gram models using Naive Bayes (NB) and Maximum Entropy (ME). Finally, a combination of machine learning methods is proposed which presents an outstanding performance in precision, recall and F1 score. After selecting the most useful methods to construct the combinational model and testing over the corpus, the final F1 score is 0.920.

* The 29th Pacific Asia Conference on Language, Information and Computing 

  Access Paper or Ask Questions

Improving Document-Level Sentiment Analysis with User and Product Context

Nov 18, 2020
Chenyang Lyu, Jennifer Foster, Yvette Graham

Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investigate incorporating additional review text available at the time of sentiment prediction that may prove meaningful for guiding prediction. Firstly, we incorporate all available historical review text belonging to the author of the review in question. Secondly, we investigate the inclusion of historical reviews associated with the current product (written by other users). We achieve this by explicitly storing representations of reviews written by the same user and about the same product and force the model to memorize all reviews for one particular user and product. Additionally, we drop the hierarchical architecture used in previous work to enable words in the text to directly attend to each other. Experiment results on IMDB, Yelp 2013 and Yelp 2014 datasets show improvement to state-of-the-art of more than 2 percentage points in the best case.

* Accepted to COLING 2020 (Oral) 

  Access Paper or Ask Questions

Visual Sentiment Analysis: A Natural DisasterUse-case Task at MediaEval 2021

Nov 22, 2021
Syed Zohaib Hassan, Kashif Ahmad, Michael A. Riegler, Steven Hicks, Nicola Conci, Paal Halvorsen, Ala Al-Fuqaha

The Visual Sentiment Analysis task is being offered for the first time at MediaEval. The main purpose of the task is to predict the emotional response to images of natural disasters shared on social media. Disaster-related images are generally complex and often evoke an emotional response, making them an ideal use case of visual sentiment analysis. We believe being able to perform meaningful analysis of natural disaster-related data could be of great societal importance, and a joint effort in this regard can open several interesting directions for future research. The task is composed of three sub-tasks, each aiming to explore a different aspect of the challenge. In this paper, we provide a detailed overview of the task, the general motivation of the task, and an overview of the dataset and the metrics to be used for the evaluation of the proposed solutions.

* 3 pages 

  Access Paper or Ask Questions

A Data Set of Internet Claims and Comparison of their Sentiments with Credibility

Nov 22, 2019
Amey Parundekar, Susan Elias, Ashwin Ashok

In this modern era, communication has become faster and easier. This means fallacious information can spread as fast as reality. Considering the damage that fake news kindles on the psychology of people and the fact that such news proliferates faster than truth, we need to study the phenomenon that helps spread fake news. An unbiased data set that depends on reality for rating news is necessary to construct predictive models for its classification. This paper describes the methodology to create such a data set. We collect our data from which is a fact-checking organization. Furthermore, we intend to create this data set not only for classification of the news but also to find patterns that reason the intent behind misinformation. We also formally define an Internet Claim, its credibility, and the sentiment behind such a claim. We try to realize the relationship between the sentiment of a claim with its credibility. This relationship pours light on the bigger picture behind the propagation of misinformation. We pave the way for further research based on the methodology described in this paper to create the data set and usage of predictive modeling along with research-based on psychology/mentality of people to understand why fake news spreads much faster than reality.

* 8 pages, 6 figures, A paper accepted at the Truth Discovery and Fact Checking: Theory and Practice SIGKDD 2019 Workshop, August 5th, Anchorage, Alaska 

  Access Paper or Ask Questions

Aspect-Sentiment Embeddings for Company Profiling and Employee Opinion Mining

Feb 22, 2019
Rajiv Bajpai, Devamanyu Hazarika, Kunal Singh, Sruthi Gorantla, Erik Cambria, Roger Zimmerman

With the multitude of companies and organizations abound today, ranking them and choosing one out of the many is a difficult and cumbersome task. Although there are many available metrics that rank companies, there is an inherent need for a generalized metric that takes into account the different aspects that constitute employee opinions of the companies. In this work, we aim to overcome the aforementioned problem by generating aspect-sentiment based embedding for the companies by looking into reliable employee reviews of them. We created a comprehensive dataset of company reviews from the famous website and employed a novel ensemble approach to perform aspect-level sentiment analysis. Although a relevant amount of work has been done on reviews centered on subjects like movies, music, etc., this work is the first of its kind. We also provide several insights from the collated embeddings, thus helping users gain a better understanding of their options as well as select companies using customized preferences.

  Access Paper or Ask Questions

Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference

Feb 12, 2020
Youwei Song, Jiahai Wang, Zhiwei Liang, Zhiyue Liu, Tao Jiang

Aspect based sentiment analysis aims to identify the sentimental tendency towards a given aspect in text. Fine-tuning of pretrained BERT performs excellent on this task and achieves state-of-the-art performances. Existing BERT-based works only utilize the last output layer of BERT and ignore the semantic knowledge in the intermediate layers. This paper explores the potential of utilizing BERT intermediate layers to enhance the performance of fine-tuning of BERT. To the best of our knowledge, no existing work has been done on this research. To show the generality, we also apply this approach to a natural language inference task. Experimental results demonstrate the effectiveness and generality of the proposed approach.

* 5 pages, 2 figures 

  Access Paper or Ask Questions