What Emotions Make One or Five Stars? Understanding Ratings of Online Product Reviews by Sentiment Analysis and XAI

@article{So2020WhatEM,
  title={What Emotions Make One or Five Stars? Understanding Ratings of Online Product Reviews by Sentiment Analysis and XAI},
  author={Chaehan So},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.00201}
}
When people buy products online, they primarily base their decisions on the recommendations of others given in online reviews. The current work analyzed these online reviews by sentiment analysis and used the extracted sentiments as features to predict the product ratings by several machine learning algorithms. These predictions were disentangled by various meth-ods of explainable AI (XAI) to understand whether the model showed any bias during prediction. Study 1 benchmarked these algorithms… Expand
Explainable Sentiment Analysis Application for Social Media Crisis Management in Retail
TLDR
This study develops an Explainable Sentiment Analysis (XSA) application for Twitter data, and proposes research propositions focused on evaluating such application in a hypothetical crisis management scenario, and illustrates the XSA application can be effective in providing the most important words addressing customers sentiment out of individual tweets. Expand

References

SHOWING 1-10 OF 33 REFERENCES
Aspect-based Sentiment Analysis on Hotel Reviews
In this project we explored varieties of supervised machine learning methods for the purpose of sentiment analysis on TripAdvisor hotel reviews. We experimented and explored with the factors thatExpand
What Makes a Helpful Online Review? A Study of Customer Reviews on Amazon.com
TLDR
Drawing on the paradigm of search and experience goods from information economics, a model of customer review helpfulness is developed and tested and indicates that review extremity, review depth, and product type affect the perceived helpfulness of the review. Expand
Aspect based Sentiment Oriented Summarization of Hotel Reviews
TLDR
This study analyzes the hotel reviews and gives information that ratings might overlook, ultimately building towards Hotel Recommender System. Expand
Machine Learning-Based Sentiment Analysis for Twitter Accounts
TLDR
A hybrid approach that involves a sentiment analyzer that includes machine learning and a comparison of techniques of sentiment analysis in the analysis of political views by applying supervised machine-learning algorithms such as Naive Bayes and support vector machines (SVM). Expand
On predicting elections with hybrid topic based sentiment analysis of tweets
TLDR
This paper introduces a novel method: Hybrid Topic Based Sentiment Analysis (HTBSA) with the aim of capturing word relations and co-occurrences in short length tweets for election prediction using tweets. Expand
Review-level aspect-based sentiment analysis using an ontology
TLDR
This work focuses on ontology-enhanced methods that complement a standard machine learning algorithm, and uses an ontology as a knowledge base for aspect-based sentiment analysis at the review-level for restaurant reviews. Expand
Classification and Regression by randomForest
TLDR
random forests are proposed, which add an additional layer of randomness to bagging and are robust against overfitting, and the randomForest package provides an R interface to the Fortran programs by Breiman and Cutler. Expand
Machine Learning Interpretability: A Survey on Methods and Metrics
TLDR
A review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics is provided. Expand
Discrete Neural Signatures of Basic Emotions.
TLDR
Brain regions contributing most to the classification accuracy included medial and inferior lateral prefrontal cortices, frontal pole, precentral and postcentral gyri, precuneus, and posterior cingulate cortex, suggesting a direct link between activity in these brain regions and the subjective emotional experience. Expand
When we like what we know – A parametric fMRI analysis of beauty and familiarity
TLDR
This paper identified clusters in which BOLD activity was correlated with individual post-scan beauty ratings, indicating that some spontaneous aesthetic evaluation takes place during reading, even if not required by the task. Expand
...
1
2
3
4
...