In recent years, the paradigm of eXplainable Artificial Intelligence (XAI) systems has gained wide research interest and beyond.
The Natural Language Processing (NLP) community is also approaching this new way of understanding AI applications: building a suite of models that provide an explanation for the decision, without affecting performance.
This is certainly not an easy task, considering the wide use of very poorly interpretable models such as Transformers, which in recent years are found to be almost ubiquitous in the NLP literature because of the great strides they have allowed.
Here we propose two different methodologies to exploit the performance of these models in a task of sentiment analysis and, in the meantime, to generate a summary that serves as an explanation of the decision taken by the system.
To compare the classification performance of the two methodologies, we used the IMDB dataset while, to assess the explainability performance, we annotated some samples of this dataset to retrieve human extractive summaries, benchmarking them with the summaries generated by the systems.

Extractive Summarization for Explainable Sentiment Analysis using  Transformers

The traditional way to address the problem of sentiment classification is based in 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.  In this work, we propose 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, particularly in tweets.  We represent the tweets using graphs, then graph similarity metrics and a Deep Learning classification algorithm are applied to produce sentiment predictions. This approach facilitates the traceability and explainability of the classification results, since it is possible to visually inspect the graphs. We compare our proposal with character n-gram embeddings based Deep Learning models to perform Sentiment Analysis. Results show that our proposal is able to outperforms classical n-gram models, with a recall up to 89% and F1-score of 88%.

Deep Learning Enhanced with Graph Knowledge for Sentiment Analysis

Lexicon-based Sentiment Analysis relies on sentiment dictionaries which are used to assign a sentiment polarity to the words of an input text. The overall sentiment of the text is then computed by means of a combining function, such as the word count, sum or average. In this short contribution we describe a detailed set of linguistic rules that allow to understand the text fragments which are semantically linked to a given concept of interest in a text. These heuristics have been designed in the spirit of the recent Interpretable AI trend, since they allow to understand the origin of sentiment for a specific term, providing more transparency and interpretation of the resulting analysis, and enabling the development of advanced and novel lexicon-based Sentiment Analysis approaches, which is the object of our currently on-going work.

ESWC 2021 Workshop X-SENTIMENT Submissions

Extractive Summarization for Explainable Sentiment Analysis using Transformers

Deep Learning Enhanced with Graph Knowledge for Sentiment Analysis

Explaining Sentiment from Lexicon