Special Issue "Deep Learning and Explainability for Sentiment Analysis"

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (30 June 2022) | Viewed by 14633

Special Issue Editors

Prof. Dr. Diego Reforgiato Recupero
E-Mail Website
Guest Editor
Department of Mathematics and Computer Science, Università Degli Studi di Cagliari, 09124 Cagliari, Spain
Interests: machine learning; semantic web; sentiment analysis; text mining; knowledge graphs
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Harald Sack
E-Mail Website
Guest Editor
FIZ Karlsruhe / KIT Karlsruhe, Karlsruhe, Germany
Interests: semantic web; knowledge engineering; multimedia retrieval; data mining; ontologies; knowledge graphs; machine learning
Dr. Danilo Dessi'
E-Mail Website
Guest Editor
FIZ Karlsruhe / KIT Karlsruhe, Karlsruhe, Germany
Interests: machine learning; semantic web; sentiment analysis; text mining; knowledge graphs

Special Issue Information

Dear Colleagues,

People use online social platforms to express opinions about products and/or services in a wide range of domains, influencing the point of view and behavior of their peers. Understanding individuals’ satisfaction is a key element for businesses, policy makers, organizations, and social institutions to make decisions. This has led to a growing amount of interest within the scientific community, and, as a result, to a host of new challenges that need to be solved. Sentiment analysis methodologies have been investigated and employed by researchers in the past to provide methodologies and resources to stakeholders. In the field of machine learning, deep learning models which combine several neural networks have emerged and have become the state-of-the-art technologies in various domains for a variety of natural language processing tasks. The most prominent deep learning solutions are combined with word embeddings. However, how to include sentiment information in word-embedding representations to boost the performances of deep learning models, as well as explain what deep learning models (often employed as a black-box) learn are questions that still remain open and need further research and development.

The investigation of these key points will answer to why and how design choices for creating embedding representations and designing deep learning should be made. This goes toward the direction of Explainable Deep Learning (XDL), whose aim is to address how deep learning systems make decisions. This Special Issue aims to foster discussions about the design, development, and use of deep learning models and embedding representations which can help to improve state-of-the-art results, and at the same time enable interpreting and explaining the effectiveness of the use of deep learning for sentiment analysis. We invite theoretical works, implementations, and practical use cases that show benefits in the use of deep learning with a high focus on explainability for various domains.

The Special Issue is focused but not limited to these topics:

  • Deep learning topics
    • Aspect-based DL and XDL models; 
    • Bias detection within DL and XDL for sentiment analysis; 
    • DL and XDL for toxicity and hate speech detection; 
    • Multilingual DL and XDL for sentiment analysis; 
    • DL and XDL for emotions detection; 
    • Weak-supervised DL and XDL for sentiment analysis; 
    • XDL design methodologies for sentiment analysis; 
    • Analysis of DL models for sentiment analysis.
  • Data representations topics
    • Word embeddings for sentiment analysis; 
    • Knowledge graph and knowledge graph embeddings for sentiment analysis; 
    • Use of external knowledge (e.g., knowledge graphs) to feed DL for sentiment analysis; 
    • Combination of existing sentiment analysis resources (e.g., SenticNet) with embedding representations; 
    • Analysis of the performance of data representations for sentiment analysis tasks 
    • Lexicon-based explainability for sentiment analysis.
  • Case studies
    • Educational environments; 
    • Healthcare systems; 
    • Scholarly discussions (e.g., peer review process discussions, mailing lists, etc.); 
    • News platforms; 
    • Mental health systems; 
    • Social networks.

Prof. Dr. Diego Reforgiato Recupero
Prof. Dr. Harald Sack
Dr. Danilo Dessi'
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (8 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
A Deep-Learning Based Method for Analysis of Students’ Attention in Offline Class
Electronics 2022, 11(17), 2663; https://doi.org/10.3390/electronics11172663 - 25 Aug 2022
Viewed by 641
Abstract
Students’ actual learning engagement in class, which we call learning attention, is a major indicator used to measure learning outcomes. Obtaining and analyzing students’ attention accurately in offline classes is important empirical research that can improve teachers’ teaching methods. This paper proposes a [...] Read more.
Students’ actual learning engagement in class, which we call learning attention, is a major indicator used to measure learning outcomes. Obtaining and analyzing students’ attention accurately in offline classes is important empirical research that can improve teachers’ teaching methods. This paper proposes a method to obtain and measure students’ attention in class by applying a variety of deep-learning models and initiatively divides a whole class into a series of time durations, which are categorized into four states: lecturing, interaction, practice, and transcription. After video and audio information is taken with Internet of Things (IoT) technology in class, Retinaface and the Vision Transformer (ViT) model is used to detect faces and extract students’ head-pose parameters. Automatic speech recognition (ASR) models are used to divide a class into a series of four states. Combining the class-state sequence and each student’s head-pose parameters, the learning attention of each student can be accurately calculated. Finally, individual and statistical learning attention analyses are conducted that can help teachers to improve their teaching methods. This method shows potential application value and can be deployed in schools and applied in different smart education programs. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
Measuring the Impact of Language Models in Sentiment Analysis for Mexico’s COVID-19 Pandemic
Electronics 2022, 11(16), 2483; https://doi.org/10.3390/electronics11162483 - 10 Aug 2022
Viewed by 743
Abstract
The world has been facing the COVID-19 pandemic, which has come with an unprecedented impact on general physical health and financial and social repercussions. The adopted mitigation measures also present significant challenges to the population’s mental health and health-related programs. It is complex [...] Read more.
The world has been facing the COVID-19 pandemic, which has come with an unprecedented impact on general physical health and financial and social repercussions. The adopted mitigation measures also present significant challenges to the population’s mental health and health-related programs. It is complex for public organizations to measure the population’s mental health to incorporate its feedback into their decision-making process. A significant portion of the population has turned to social media to express the details of their daily life, making these public data a rich field for understanding emotional and mental well-being. To this end, by using open sentiment analysis tools, we analyzed 760,064,879 public domain tweets collected from a public access repository to examine the collective shifts in the general mood about the pandemic evolution, news cycles, and governmental policies. Several modern language models were evaluated and compared using intrinsic and extrinsic tasks, that is, the sentiment analysis evaluation of public domain tweets related to the COVID-19 pandemic in Mexico. This study provides a fair evaluation of state-of-the-art language models, such as BERT and VADER, showcasing their metrics and comparing their performance against a real-world task. Results show the importance of selecting the correct language model for large projects such as this one, for there is a need to balance costs with the model’s performance. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
Emotion Analysis and Dialogue Breakdown Detection in Dialogue of Chat Systems Based on Deep Neural Networks
Electronics 2022, 11(5), 695; https://doi.org/10.3390/electronics11050695 - 24 Feb 2022
Cited by 1 | Viewed by 1100
Abstract
In dialogues between robots or computers and humans, dialogue breakdown analysis is an important tool for achieving better chat dialogues. Conventional dialogue breakdown detection methods focus on semantic variance. Although these methods can detect dialogue breakdowns based on semantic gaps, they cannot always [...] Read more.
In dialogues between robots or computers and humans, dialogue breakdown analysis is an important tool for achieving better chat dialogues. Conventional dialogue breakdown detection methods focus on semantic variance. Although these methods can detect dialogue breakdowns based on semantic gaps, they cannot always detect emotional breakdowns in dialogues. In chat dialogue systems, emotions are sometimes included in the utterances of the system when responding to the speaker. In this study, we detect emotions from utterances, analyze emotional changes, and use them as the dialogue breakdown feature. The proposed method estimates emotions by utterance unit and generates features by calculating the similarity of the emotions of the utterance and the emotions that have appeared in prior utterances. We employ deep neural networks using sentence distributed representation vectors as the feature. In an evaluation of experimental results, the proposed method achieved a higher dialogue breakdown detection rate when compared to the method using a sentence distributed representation vectors. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
Lexicon-Based vs. Bert-Based Sentiment Analysis: A Comparative Study in Italian
Electronics 2022, 11(3), 374; https://doi.org/10.3390/electronics11030374 - 26 Jan 2022
Cited by 9 | Viewed by 2586
Abstract
Recent evolutions in the e-commerce market have led to an increasing importance attributed by consumers to product reviews made by third parties before proceeding to purchase. The industry, in order to improve the offer intercepting the discontent of consumers, has placed increasing attention [...] Read more.
Recent evolutions in the e-commerce market have led to an increasing importance attributed by consumers to product reviews made by third parties before proceeding to purchase. The industry, in order to improve the offer intercepting the discontent of consumers, has placed increasing attention towards systems able to identify the sentiment expressed by buyers, whether positive or negative. From a technological point of view, the literature in recent years has seen the development of two types of methodologies: those based on lexicons and those based on machine and deep learning techniques. This study proposes a comparison between these technologies in the Italian market, one of the largest in the world, exploiting an ad hoc dataset: scientific evidence generally shows the superiority of language models such as BERT built on deep neural networks, but it opens several considerations on the effectiveness and improvement of these solutions when compared to those based on lexicons in the presence of datasets of reduced size such as the one under study, a common condition for languages other than English or Chinese. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
Sentiment Analysis in Twitter Based on Knowledge Graph and Deep Learning Classification
Electronics 2021, 10(22), 2739; https://doi.org/10.3390/electronics10222739 - 10 Nov 2021
Cited by 4 | Viewed by 1655
Abstract
The traditional way to address the problem of sentiment classification is based on 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 [...] Read more.
The traditional way to address the problem of sentiment classification is based on 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. This work proposes 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, such as posts on Twitter. In this proposal, tweets are represented as graphs; then, graph similarity metrics and a Deep Learning classification algorithm are applied to produce sentiment predictions. This approach facilitates the traceability and interpretability of the classification results, thanks to the integration of the Local Interpretable Model-agnostic Explanations (LIME) model at the end of the pipeline. LIME allows raising trust in predictive models, since the model is not a black box anymore. Uncovering the black box allows understanding and interpreting how the network could distinguish between sentiment polarities. Each phase of the proposed approach conformed by pre-processing, graph construction, dimensionality reduction, graph similarity, sentiment prediction, and interpretability steps is described. The proposal is compared with character n-gram embeddings-based Deep Learning models to perform Sentiment Analysis. Results show that the proposal is able to outperforms classical n-gram models, with a recall up to 89% and F1-score of 88%. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
Explainable Sentiment Analysis: A Hierarchical Transformer-Based Extractive Summarization Approach
Electronics 2021, 10(18), 2195; https://doi.org/10.3390/electronics10182195 - 08 Sep 2021
Cited by 5 | Viewed by 1600
Abstract
In recent years, the explainable artificial intelligence (XAI) paradigm is gaining wide research interest. The natural language processing (NLP) community is also approaching the shift of paradigm: building a suite of models that provide an explanation of the decision on some main task, [...] Read more.
In recent years, the explainable artificial intelligence (XAI) paradigm is gaining wide research interest. The natural language processing (NLP) community is also approaching the shift of paradigm: building a suite of models that provide an explanation of the decision on some main task, without affecting the performances. It is not an easy job for sure, especially when very poorly interpretable models are involved, like the almost ubiquitous (at least in the NLP literature of the last years) transformers. Here, we propose two different transformer-based methodologies exploiting the inner hierarchy of the documents to perform a sentiment analysis task while extracting the most important (with regards to the model decision) sentences to build a summary as the explanation of the output. For the first architecture, we placed two transformers in cascade and leveraged the attention weights of the second one to build the summary. For the other architecture, we employed a single transformer to classify the single sentences in the document and then combine the probability scores of each to perform the classification and then build the summary. We compared the two methodologies by using the IMDB dataset, both in terms of classification and explainability performances. To assess the explainability part, we propose two kinds of metrics, based on benchmarking the models’ summaries with human annotations. We recruited four independent operators to annotate few documents retrieved from the original dataset. Furthermore, we conducted an ablation study to highlight how implementing some strategies leads to important improvements on the explainability performance of the cascade transformers model. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
Real-Time Sentiment Analysis for Polish Dialog Systems Using MT as Pivot
Electronics 2021, 10(15), 1813; https://doi.org/10.3390/electronics10151813 - 28 Jul 2021
Cited by 1 | Viewed by 1396
Abstract
We live in a time when dialogue systems are becoming a very popular tool. It is estimated that in 2021 more than 80% of communication with customers on the first line of service will be based on chatbots. They enter not only the [...] Read more.
We live in a time when dialogue systems are becoming a very popular tool. It is estimated that in 2021 more than 80% of communication with customers on the first line of service will be based on chatbots. They enter not only the retail market but also various other industries, e.g., they are used for medical interviews, information gathering or preliminary assessment and classification of problems. Unfortunately, when these work incorrectly it leads to dissatisfaction. Such systems have the possibility of contacting a human consultant with a special command, but this is not the point. The dialog system should provide a good, uninterrupted and fluid experience and not show that it is an artificial creation. Analysing the sentiment of the entire dialogue in real time can provide a solution to this problem. In our study, we focus on studying the methods of analysing the sentiment of dialogues based on machine learning for the English language and the morphologically complex Polish language, which also represents a language with a small amount of training resources. We analyse the methods directly and use the machine translator as an intermediary, thus checking the quality changes between models based on limited resources and those based on much larger English but machine translated texts. We manage to obtain over 89% accuracy using BERT-based models. We make recommendations in this regard, also taking into account the cost aspect of implementing and maintaining such a system. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Article
An Assessment of Deep Learning Models and Word Embeddings for Toxicity Detection within Online Textual Comments
Electronics 2021, 10(7), 779; https://doi.org/10.3390/electronics10070779 - 25 Mar 2021
Cited by 11 | Viewed by 2346
Abstract
Today, increasing numbers of people are interacting online and a lot of textual comments are being produced due to the explosion of online communication. However, a paramount inconvenience within online environments is that comments that are shared within digital platforms can hide hazards, [...] Read more.
Today, increasing numbers of people are interacting online and a lot of textual comments are being produced due to the explosion of online communication. However, a paramount inconvenience within online environments is that comments that are shared within digital platforms can hide hazards, such as fake news, insults, harassment, and, more in general, comments that may hurt someone’s feelings. In this scenario, the detection of this kind of toxicity has an important role to moderate online communication. Deep learning technologies have recently delivered impressive performance within Natural Language Processing applications encompassing Sentiment Analysis and emotion detection across numerous datasets. Such models do not need any pre-defined hand-picked features, but they learn sophisticated features from the input datasets by themselves. In such a domain, word embeddings have been widely used as a way of representing words in Sentiment Analysis tasks, proving to be very effective. Therefore, in this paper, we investigated the use of deep learning and word embeddings to detect six different types of toxicity within online comments. In doing so, the most suitable deep learning layers and state-of-the-art word embeddings for identifying toxicity are evaluated. The results suggest that Long-Short Term Memory layers in combination with mimicked word embeddings are a good choice for this task. Full article
(This article belongs to the Special Issue Deep Learning and Explainability for Sentiment Analysis)
Show Figures

Figure 1

Back to TopTop