A Pre-Trained Model for Aspect-based Sentiment Analysis Task: using Online Social Networking

Sentiment analysis is becoming rapidly important for exploring social media Bangla text. The lack of sufficient resources is considered to be an important challenge for Aspect Based Sentiment Analysis (ABSA) of the Bangla language. The ABSA is a technique that divides the text and defines its sentiment based on its aspects. In this paper, we developed a high-quality Bangla ABSA annotated dataset namely BANGLA_ABSA. The datasets are labelled with aspects category and their respective sentiment polarity to do the ABSA task in Bangla. Four open domains namely Restaurant, Movie, Mobile phone, and Car are considered to make the dataset. The datasets are called Restaurant_ABSA, Movie_ABSA, Mobile_phone_ABSA, and Car_ABSA respectively that contain 801, 800, 975, and 1149 comments. All the comments are either complex or compound sentences. We created the dataset manually and annotated the same by exerting opinions. We organized the dataset as three tuples in Excel format namely 〈Id, Comment, {Aspect category, Sentiment Polarity}〉. These data are very important that facilitate the efficient handling of sentiment for any machine learning and deep learning research, especially for Bangla text.

A number of businesses, such as TripAdvisor, Open Table, and Yelp, have successfully utilized aspect-based sentiment analysis in order to gain insights from reviews provided by customers and enhance the quality of their goods or services. Businesses are able to swiftly discover any unfavorable sentiment or possible harm to their brand when they analyze client input across numerous aspects from social media, online reviews, and conversations with customer care representatives. This study aims to explain how aspect-based semantic analysis of market-collected user-generated data through performance comparisons of Doc2vec and TF-IDF vectorization. Both Doc2Vec and TF-IDF have their own distinctive qualities, which might vary according on the nature of the job, the dataset, and the volume of the available training data. For the objectives of this research, the data was obtained from several of fashion merchants that run their companies by means of the Shopee platform, which is a well-known online marketplace platform in Indonesia. In this research, the accuracy and F1 Score achieved by Doc2Vec vectorization was superior to those achieved by TF-IDF vectorization. Our findings shows that Doc2Vec vectorization is better for classifying customer ratings because it can pull out the semantic meaning of words in a document. The findings also shows that the score of c and gamma parameter have significant impact to the score of Accuracy and F1 Score of the classifier.By precisely categorizing client sentiment, this study enables businesses to improve their services, respond to customers' problems, and increase their customer satisfaction.

Aspect-Based Sentiment Analysis (ABSA) is a Natural Language Processing (NLP) task that extracts referred aspects from text and assigns polarities to opinions about those aspects. Most research on ABSA focuses on English. Only a few ABSA works deal with the Portuguese language. In this work, we used BERTimbau to create a Question-Answer approach to ABSA in Portuguese. First, we post-trained this model with text from the same domain as our target corpus. Then, we constructed an auxiliary sentence from the aspect and converted ABSA to a sentence-pair classification task, such as question answering (QA) and natural language inference (NLI). Our experiments show that ABSA based on BERT for Portuguese achieved Balanced Accuracy (BACC) of 77% on a corpus of reviews about the accommodation sector using a post-trained model with QA approach.

Aspect-based sentiment analysis (ABSA) has become an essential field in Natural Language Processing (NLP) in recent years.ABSA not only categorizes sentiment as positive, negative, or neutral but also understands the specific aspects or topics discussed in the text review.This study focuses on two important elements of ABSA: Aspect Term Extraction (ATE) and Aspect Sentiment Classification (ASC).This study uses a combination of Sentence Embedding (SBERT) techniques, Part-of-Speech tagging, cosine-similarity calculation to assess words with their respective aspect labels, and the sparse attention mechanism (BIGBIRD) method, which has been proven to increase accuracy effectively and is effective in terms of time and memory usage.By applying this method to two hotel review datasets, Traveloka Review and Semeval 2016 dataset, it is proven to work well on two ABSA tasks, namely ATE and ASC.The results of the ATE test obtained an accuracy of 0.99, and the ASC test obtained an accuracy of 0.89.This study contributes to the advancement of ABSA by introducing a new methodology that improves the accuracy of aspect term extraction and sentiment classification.Additionally, it identifies avenues for future research, including exploring additional techniques to improve model performance and address potential limitations.

Techniques and methods for examining users’ feelings, emotions, and views in text or other media are known as ”sentiment analysis,” this phrase is used frequently. In many areas, including marketing and online social media, analysis of user and consumer opinions has always been essential to decision-making processes. The development of new methodologies that concentrate on analysing the sentiment associated with specific product characteristics, such as aspect-based sentiment analysis (ABSA), was prompted by the need for a deeper understanding of these opinions. Despite the growing interest in this field, some misunderstanding exists about ABSA’s core ideas. Even though sentiment, affect, emotion, and opinion refer to various ideas, they are frequently used synonymously. This ambiguity commonly causes user opinions to be analysed incorrectly. This work provides an overview of ABSA and the issue of overfitting. Following this analysis, we improved the model by enhancing the accuracy and F1 score of the existing model by fine-tuning the technique. Our model outperformed the others, achieving the best results for the restaurant dataset with an 85.02 accuracy and a 79.19 F1 score, respectively.

In the ever-expanding digital landscape, the abundance of user-generated content on consumer platforms such as Booking and TripAdvisor offers a rich source of information for both travellers and hoteliers. Sentiment analysis, a fundamental research task of natural language processing (NLP) is used for mining sentiments and opinions within this vast reservoir of text reviews. A more specific type of sentiment analysis, i.e., aspect-based sentiment analysis (ABSA), is used when processing customer reviews is required. In ABSA, we aim to capture aspect-level sentiments and intricate relationships between various aspects within reviews. This article proposes a novel approach to ABSA by introducing a novel technique of word sense disambiguation (WSD) and integrating it with the Transformer architecture bidirectional encoder representations from Transformers (BERT) and graph convolutional networks (GCNs). The proposed approach resolves the intriguing ambiguities of the words and represents the review data as a complex graph structure, facilitating the modeling of intricate relationships between different aspects. The combination of bidirectional long short-term memory (BiLSTM) and GCN proves effective in capturing inter-dependencies among various aspects, providing a nuanced understanding of customer sentiments. The experiments are conducted on the RABSA dataset (an enhanced and richer hotel review data collection), and results demonstrate that our approach outperforms previous baselines, showcasing the effectiveness of integrating WSD in ABSA. Furthermore, an ablation study confirms the significant contribution of the WSD module to the overall performance. Moreover, we explore different similarity measures and find that cosine similarity yields the best results when identifying the real sense of a word in a given sentence using WordNet. The findings of our work and future work related to our work create lots of interest for people in the tourism and hospitality industry. This research gives another boost to the concept of the potential of NLP techniques in sentiment analysis. It emphasizes that if we combine the potential of NLP techniques along with state-of-the-art machine learning frameworks, we can shape the future of this field.

Aspect-based Sentiment analysis (ABSA) is a rapidly growing field of research in natural language processing. ABSA is a fine-grained task of Sentiment analysis. How to capture precise sentiment expressions in a sentence towards the specific aspect remains a challenge. In this paper, we propose a novel neural network, named Multiple-element Attention LSTM (MEA-LSTM) to alleviate the problem of self-attention or binary-element attention used in the ABSA task. These attention mechanisms mentioned above are weak attention, they ignore the information of aspect target or sentence representation. To capture the precise sentiment expressions, we make use of multiple-element attention to assign different importance degrees of different words in a sentence. To store these informative aspect-dependent representations, extra representation memory is designed. Part of speech (POS) is an important feature in identifying the sentiment expressions in the ABSA task. We combine POS with the LSTM in the proposed MEA-LSTM. Experimental results show that our proposed model acquires state-of-the-art accuracy at both restaurant and laptop datasets. Besides, a rule of thumb about choosing the number of hops is given on both datasets.

As a fine-grained sentiment analysis subtask in the natural language processing (NLP) community, aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity of the aspect terms according to the given sentence. In previous research, external affective knowledge has been utilized to enhance the representation of the sentiment information contained in the text, which has achieved impressive progress in ABSA task. However, it is worth noting that the external knowledge employed is usually leveraged from the single-dimensional perspective, which lacks diversified and multiple-dimensional exploration and leads to insufficient comprehension of the complex sentiment information. Thus, this paper proposes a novel ABSA network to fully exploit the sentiment features from triple dimensions, namely the psychology knowledge assisted graph attention networks (VADGAT). Preliminarily, to obtain the task-relevant semantic representation, an aspect-oriented template is devised firstly to guide the fine-tuning of the pre-trained language model. Besides, to fully leverage the triple-dimensional sentiment, they are injected into the normal dependency graph to construct three mutually independent adjacent matrices, which are implemented by graph attention networks (GAT) to extract the relations among graph nodes, progressively. Meanwhile, to be treated as the fourth dimension of human beings’ sentiment, SenticNet is also leveraged to enhance the sentiment intensity of the words in the text, which are expected to highlight implicit information and support the final sentiment inference. Moreover, an intentional shadow network is devised and leveraged to reinforce the screening ability of sentiment information, which is integrated with the mainstream representation proportionally. Furthermore, to improve the effectiveness of this innovative strategy, this paper utilizes the Jensen–Shannon divergence to evaluate the similarity between the mainstream and the shadow modules and optimizes the designed VADGAT eventually. To validate the effectiveness of the proposed approach, this paper conducted extensive experiments on five publicly available datasets, and the results show that the approach outperforms the state-of-the-art methods.

Internet usage has increased social media over the past few years, significantly impacting public opinion on online social networks. Nowadays, these websites are considered the most appropriate place to express feelings and opinions. The popular social media site Twitter offers valuable insight into people’s thoughts. Throughout the conflict between Russia and Ukraine, people from all over the world have expressed their opinions. In this study, ”machine–learning” & ”deep–learning” techniques are used to understand people’s emotions and their views about this war are revealed. This study unveils a novel deep-learning approach that merges the best features of the sequence and transformer models while fixing their respective flaws. The model combines Roberta with ABSA(Aspect based sentiment analysis) and Long Short-Term Memory for sentiment analysis. A large dataset of geographically tagged tweets related to the Ukraine-Russia war was collected from Twitter. We analyzed this dataset using the Roberta-based sentiment model. In contrast, the Long Short-Term Memory model can effectively capture long-distance contextual semantics. The Robustly optimized BERT with ABSA approach maps words into a compact, meaningful word embedding space. The accuracy of the suggested hybrid model is 94.7%, which is higher than the accuracy of the state-of-the-art techniques.

Due to the rapid increase in User-Generated Content (UGC) data, opinion mining, also called sentiment analysis, has attracted much attention in both academia and industry. Aspect-Based Sentiment Analysis (ABSA), a subfield of sentiment analysis, aims to extract the aspect and the corresponding sentiment simultaneously. Previous works in ABSA may generate undesired aspects, require a large amount of training data, or produce unsatisfactory results. This paper proposes a Graph Neural Network based method to automatically generate aspect-specific sentiment words using a small number of aspect seed words and general sentiment words. It subsequently leverages the aspect-specific sentiment words to improve the Joint Aspect-Sentiment Autoencoder (JASA) model. We conduct experiments on two datasets to verify the proposed model. It shows that our approach has better performance in the ABSA task when compared with previous works.KeywordsAspect-based sentiment analysisAttention mechanismAutoencoderText graph convolution networkText mining

IFusionQuad: A novel framework for improved aspect-based sentiment quadruple analysis in dialogue contexts with advanced feature integration and contextual CloBlock

Sentiment analysis (SA) is one of the most active and rapidly developing research areas in both information retrieval and text mining fields of computer science. SA is the process of analysing, handling, generalizing, and reasoning about user sentiments, opinions, and emotions hidden within the text by using sentiment. There are various categories of levels of SA: (1) document-level, (2) sentence-level, and (3) aspect-level. This paper is focused on sorting out some Aspect-based sentiment analysis (ABSA) works. ABSA is one of the primary tasks in sentiment analysis, which involves identifying the expression of an opinion or sensation of an object in a particular dimension or feature. ABSA involves two primary subtasks: (1) aspect extraction and (2) aspect-based sentiment classification. In contrast to document-and sentence-based sentiment analysis, ABSA simultaneously considers sentiment and target information. Generally, the ABSA methods can be categorized into Transformer based ABSA and Graph Neural Network based ABSA. This paper introduces some popular frameworks, datasets, and evaluation metrics of ABSA tasks based on the above-proposed classification and methodology.

The rapidly evolving landscape of Aspect-Based Sentiment Analysis (ABSA) in the realm of natural language processing necessitates innovative approaches to comprehend and interpret the intricate nature of sentiments expressed in textual data. Traditional ABSA methods have often struggled with the nuanced sentiments inherent in various textual sources, limited in their ability to adapt to domain-specific vernacular and context. This study introduces a novel approach that synergizes rule mining with advanced deep learning techniques, aiming to address these limitations and enhance the precision and contextual understanding in sentiment analysis. Our proposed model integrates rule-based systems with deep learning Transformers, a method recognized for its effectiveness in extracting structured, domain-specific insights. This integration results in a significant enhancement in the model's ability to capture nuanced sentiments, as demonstrated by an 8.5% increase in aspect-based sentiment analysis precision and an 8.3% improvement in accuracy over existing methods. The model employs a combination of techniques including Bi-LSTM, BiGRU-CRF with RNNs, and ontology mapping operations, forming a Hybrid Multi-Level Architecture that effectively captures both sequential data relationships and semantic context. Additionally, the model incorporates Cross-Domain Transfer Learning, utilizing BERT-based pre-trained models with added layers for contextual semantics, which has shown notable generalization capabilities across various domains. Furthermore, this study refines evaluation parameters, tailoring metrics such as domain-specific accuracy, recall, and precision to more accurately assess model performance in particular domains. This is especially pertinent in our analysis of Twitter datasets specific to industries like finance and healthcare. The inclusion of Temporal Dynamics and Aspect Summarization, using techniques like the VARMAx process, provides insights into the evolution of sentiments and aspects over time, an aspect crucial for longitudinal sentiment analysis. The comprehensive testing of our model on diverse spatial and temporal datasets reveals not only improved precision and accuracy in sentiment analysis but also a reduction in delay, demonstrating its efficiency and responsiveness. The study's findings indicate that our approach could significantly impact fields reliant on sentiment analysis, such as market analysis, public opinion research, and social media monitoring, providing a more nuanced and accurate understanding of consumer sentiments and trends. This paper's contribution lies in its innovative amalgamation of rule-based and deep learning techniques, tailored evaluation metrics, and its emphasis on temporal dynamics, setting a new precedent in the field of ABSA and opening avenues for further research and application in real-world scenarios.

User-generated content (UGC) is a promising tool to assist consumers in hotel decision-making in an online environment. Existing studies on extracting sentiment opinions based on dependency parsing in aspect-based sentiment analysis (ABSA) are limited and rarely consider the importance of keywords and risk preferences of consumers to positive and negative ratings. To fill this gap, this study develops a decision-making model to select hotels based on UGC. First, the TextRank method is used to determine criteria and keywords, and 11 rules are proposed to identify potential sentiment opinions about specific keywords based on dependent parsing in ABSA. Then, a criteria value calculation method is proposed by combining sentiment scores and aspect-level ratings, where prospect theory is employed to portray different risk preferences of consumers for positive and negative ratings. Next, criteria values are input into a fuzzy inference system (FIS), and 29 linguistic rules are proposed to model the non-linear relationship between criteria and hotel performance. The applicability of the proposed method is verified by ranking 11 hotels in Chengdu city on Tripadvisor.com. Comparative analysis is given to demonstrate the effectiveness of the proposed model. Management implications are provided for practitioners to improve hotel management quality.

Background: Mobile app usage is increasing in the digital age, with Ride-Hailing app becoming the primary example of this trend. To obtain valuable understanding of how people perceive and interact with mobile app, user reviews on platforms such as Google Play are usually analyzed. This analysis can assist developers to identify areas for improvement in both Ride-hailing and Google Play App. A promising method that can be used to analyze user perception in this instance is Aspect-Based Sentiment Analysis (ABSA). Objective: This research aimed to apply ABSA to user reviews using Bidirectional Encoder Representations from Transformers (BERT) models. In this context, aspect identification and topic modeling were performed by using Latent Dirichlet Allocation (LDA). The model extracted topics from the reviews and used Generative Artificial Intelligence (GenAI) to define the aspects of the topics to further enhance the analysis. For consistency and accuracy, the method included sentiment annotation by a human annotator. Methods: A total of two datasets were used in this research, with the first collected by scraping user reviews of Ride-Hailing App while the second was obtained from Kaggle, and to identify relevant topics, modeling was performed using LDA. These topics were then categorized into aspects using GenAI, covering areas, such as customer experience, service, payment, app features, task management, and event management. Subsequently, sentiment labeling was conducted using human annotators to provide a reliable baseline. BERT model was then used to classify sentiment with aspect hints, and the evaluation included calculations of accuracy, precision, recall, and F1-score. Results: The results showed that BERT model achieved the highest accuracy of 97% in sentiment analysis across all datasets. Conclusion: This research provided valuable understanding of user experience and established a strong ABSA framework for analyzing user reviews using LDA, Aspect Annotation, GenAI, and BERT sentiment models. Future research could expand this method to other app categories and incorporate real-time ABSA for continuous monitoring and dynamic feedback. Keywords: User Reviews, Aspect-Based Sentiment Analysis (ABSA), Sentiment Analysis, Topic Modeling, Generative Artificial Intelligence (GenAI)