Traversing the landscape of aspect-based sentiment analysis: Delving deeper into techniques, trends, and future directions

The tourism sector in Indonesia experienced growth and made a positive contribution to the national economy, but this growth has yet to reach its target. Therefore, the government of Indonesia has implemented a sustainable tourism development program by establishing ten priority tourism destinations. Aspect-based sentiment analysis (ABSA) towards tourist attraction reviews can assist the government in developing potential goals. The ABSA process compares with two deep learning models (LSTM and Bi-LSTM), which are considered to obtain good performance in text analysis. The shortcomings of previous ABSA research should have examined the performance of the aspect classification and sentiment classification models sequentially. This makes the performance obtained from the ABSA task invalid. Thus, this study is conducted to determine the version of the aspect classification model and the sentiment classification model individually and simultaneously. This study aims to develop an aspect-based tourist attraction sentiment analysis as an intelligent system solution for sustainable tourism development by applying the binary relevance mechanism and the best deep learning model from LSTM or Bi-LSTM. The test results showed that Bi-LSTM was superior in aspect and sentiment classification individually and simultaneously. Likewise, the aspect classification and sentiment classification test results sequentially Bi-LSTM outperformed that of LSTM. The average accuracy and f1 score of Bi-LSTM are 92.22% and 71,06%. Meanwhile, LSTM obtained 90,63% of average precision and 70,4% of f1 score.

A survey on aspect base sentiment analysis methods and challenges

Extracting sentiment from news text, social media and blogs has recently gained increasing interest in economics and finance. Despite many successful applications of sentiment analysis (SA) in these domains, the range of semantic techniques employed is still limited and predominantly focused on the detection of sentiment at a coarse-grained level. This paper proposes a novel methodology for Fine-Grained Aspect-based Sentiment (FiGAS) analysis. The aim is to identify the sentiment associated with specific topics of interest in each sentence of a document and to assign real-valued polarity scores between -1 and +1 to those topics. The proposed approach is unsupervised and customised to the economic and financial domains by using a specialised lexicon provided by us along with the FiGAS source code. Our lexicon-based SA approach relies on a detailed set of semantic polarity rules that allow understanding of the origin of sentiment – in the spirit of the recent trend on Interpretable AI. We provide an in-depth comparison of the performance of the FiGAS algorithm with other popular lexicon-based SA approaches in predicting a humanly annotated dataset in the economic and financial domains. Our results indicate that FiGAS statistically outperforms the other methods by providing a sentiment score that is closer to those of human annotators.

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.

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.

In the processing of data produced by users, aspect based sentiment analysis (ABSA) studies are carried out today instead of classical sentiment analysis approaches. ABSA enables the determination of detailed feelings and thoughts for each component of the product or service in a user post. Using ABSA, it is possible to determine the weak and strong aspects of the tourism centers in line with the visitor comments about the tourist places. The concept of smart tourism has started to attract a lot of attention in recent years. Smart tourism is an artificial intelligence-based solution that offers the necessary systems for comfortable travel to visitors. Developing artificial intelligence-based solutions such as ABSA for tourism centers in Turkey, tourism centers can be turned into attractions. One of the most important tasks of ABSA is the extraction of aspect terms, that is, the extraction of tourism center features/aspects. The lack of a large-scale corpus labeled for this task in the Turkish language is one of the obstacles for researchers in this field. In this study, a new corpus has been created for smart tourism and ABSA. Moreover, visitor reviews to important tourism centers in Turkey were collected and labeled manually by seven different annotators as aspect term-sentiment pairs for ABSA. Latent Dirichlet Allocation (LDA) algorithm was used as a baseline approach for extracting aspect terms from visitor reviews. The created dataset has been uploaded to GitHub for all researchers.

Compared to broad sentiment analysis, aspect-based sentiment analysis (ABSA), which aims to predict the sentiment polarities of the designated features or entities in text, can produce more precise results. Product reviews and social media comments are examples of texts that can be used to identify and analyze sentiments. Another type of text analysis is known as sentiment analysis subtask, or ABSA. Deep learning methods have demonstrated efficacy in managing the intricacy of natural language and obtaining subtle emotions linked to many facets of a good or service. Deep learning has become increasingly popular in many applications, and in recent years, both the academic and industry communities have given ABSA a great deal of attention. Overall, ABSA’s deep learning efforts have been successful in advancing sentiment analysis skills, which has given rise to important insights into how consumers view and respond to various features of goods and services. Deep learning-based methods are probably going to have a big impact on how sentiment analysis apps develop in the future as technology keeps developing. The size of the dataset, the task’s difficulty, and the computer resources available all play a role in the deep learning method selection. To attain optimal performance, many state-of-the-art ABSA models pretrain on huge corpora and then fine-tune on task-specific datasets.

As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been attracting considerable interest in the last decade. To handle ABSA in different scenarios, various tasks are introduced for analyzing different sentiment elements and their relations, including the aspect term, aspect category, opinion term, and sentiment polarity. Unlike early ABSA works focusing on a single sentiment element, many compound ABSA tasks involving multiple elements have been studied in recent years for capturing more complete aspect-level sentiment information. However, a systematic review of various ABSA tasks and their corresponding solutions is still lacking, which we aim to fill in this survey. More specifically, we provide a new taxonomy for ABSA which organizes existing studies from the axes of concerned sentiment elements, with an emphasis on recent advances of compound ABSA tasks. From the perspective of solutions, we summarize the utilization of pre-trained language models for ABSA, which improved the performance of ABSA to a new stage. Besides, techniques for building more practical ABSA systems in cross-domain/lingual scenarios are discussed. Finally, we review some emerging topics and discuss some open challenges to outlook potential future directions of ABSA.

Reading massive amounts of user-generated text and pulling out the relevant aspects and opinions is a complicated process. Summaries, on the other hand, help busy people who only have a little bit of time to read get the gist of the information quickly. Text summarization is the process of taking the original text and making a shorter version of it that still has all of its informational value and main idea. Humans have a hard time summarizing long texts by hand. Different ways to summarize a text can be put into groups based on the more general techniques of extractive and abstractive summarization. The research paper discusses the need for generating aspect-based summaries and Sentiment analysis. A framework is proposed based on extracting coherent aspects from the reviews and applying the extractive summarization method to generate summaries. In addition, providing insights into the reviews of tourist attractions by using aspect-based sentiment analysis. The results are evaluated using crowdsourcing, Fairsumm, and Centroid method. The crowdsourcing method gives the best result on aspect-based summaries.

Aspect-based (aspect-level) sentiment analysis is an important task in fine-grained sentiment analysis, which aims to automatically infer the sentiment towards an aspect in its context. Previous studies have shown that utilizing the attention-based method can effectively improve the accuracy of the aspect-based sentiment analysis. Despite the outstanding progress, aspect-based sentiment analysis in the real-world remains several challenges. (1) The current attention-based method may cause a given aspect to incorrectly focus on syntactically unrelated words. (2) Conventional methods fail to identify the sentiment with the special sentence structure, such as double negatives. (3) Most of the studies leverage only one vector to represent context and target. However, utilizing one vector to represent the sentence is limited, as the natural languages are delicate and complex. In this paper, we propose a knowledge guided capsule network (KGCapsAN), which can address the above deficiencies. Our method is composed of two parts, a Bi-LSTM network and a capsule attention network. The capsule attention network implements the routing method by attention mechanism. Moreover, we utilize two prior knowledge to guide the capsule attention process, which are syntactical and n-gram structures. Extensive experiments are conducted on six datasets, and the results show that the proposed method yields the state-of-the-art.

With the advent and rapid advancement of text mining technology, a computer-based approach used to capture sentiment standpoints from data in textual form is increasingly becoming a promising field. Detailed information about sentiment can be provided using aspect-based sentiment analysis, which can be used in better decision-making. This study aims to study, observe, and classify previous methods used in aspect-based sentiment analysis. A systematic review is adopted as the method used to collect and review papers to achieve this research's aim. Papers focused on sentiment analysis, aspect extraction, and aspect aggregation from different academic databases such as Scopus, ScienceDirect, IEEE Explore, and Web of Science were gathered based on the inclusion and exclusion criteria of the study. The gathered papers were further reviewed to answer the stated research questions. The findings from the research show the most used methods for aspect extraction, sentiment analysis, and aspect aggregation in aspect-based sentiment analysis. This research offers a robust synthesis of evidence to guide further academic exploration in sentiment analysis.

Sentiment analysis(SA) has become crucial in Natural Language Processing(NLP), allowing valuable perceptions from user-generated content. Aspect-based sentiment analysis(ABSA), focusing on identifying sentiment towards specific aspects, remains challenging, especially for resource-scarce languages like Hindi. Deep learning has proven effective for ABSA in English, but applying these techniques to Hindi presents challenges due to its complex morphology, limited labeled datasets, and contextual ambiguities. Pre-trained large language models, based on transformer architectures, have become standard for NLP tasks, valuable for low-resource languages. This paper introduces a hybrid model, Hi-BERT, combining rule-based aspect extraction with a transformer based multilingual BERT architecture for sentiment analysis. Hi-BERT addresses ABSA challenges in Hindi by integrating a POS tagger with a deep learning framework. The increasing prevalence of online reviews in Hindi necessitates more nuanced sentiment analysis to understand customer feedback effectively. Hi-BERT addresses this by focusing on aspect-level sentiment analysis, extracting aspects using POS tagging, and employing a pre trained multilingual BERT model for multi-class classification. This hybrid approach aims to improve ABSA accuracy in Hindi, offering valuable insights for businesses.

Aspect-based Sentiment Analysis (ABSA) is a subdomain of Sentiment Analysis (SA) that focuses on detecting the sentiment toward features of a product or particular aspects, experience, or service. ABSA targets to go beyond simple sentiment classification of a sentence or document and present a more granular study of sentiment towards different aspects. ABSA has several real-time applications, which include social media monitoring, customer feedback analysis, and product reviews. Many difficulties exist in ABSA, including dealing with language variability and complexity, sentiment subjectivity, and managing multiple aspects in a single sentence. Recently, Deep Learning (DL) methods continued to be an active area of research and proved a promising model in ABSA. This study focuses on designing and developing ABSA models using DL concepts. The presented ABSA model aims to identify the sentiments in the direction of particular aspects or features of a product, service, or experience. The presented approach initially accomplishes diverse phases of data pre-processing to convert the input data meaningfully. In addition, the word2vec model is applied as a feature extraction approach. For sentiment analysis, three DL models are employed, namely Hopfield Network (HN), Convolutional Neural Network (CNN), and Bidirectional Long Short Term Memory (BiLSTM) approaches. The experimental validation of the DL models occurs utilizing a benchmark dataset. The simulation values highlighted that the CNN model exhibits improved sentiment classification results over other DL models.

Sentiment analysis, often known as opinion mining, is a technique used in natural language processing to determine the emotional undertone of a document. This is a common method used by organizations to identify and group ideas regarding a certain good, service, or concept. In business sectors, sentiment analysis is crucial in decision-making. Aspect-based sentiment analysis is a type of sentiment analysis that helps in company’s overall improvement by letting than know which characteristics of their products they should enhance in response to client’s feedback in order to turn them into top sellers. Many researchers in this area applied machine learning and deep learning approaches. There are issues regarding performance and accuracy in conventional machine learning sentiment analysis approaches. Thus, there is a need to improve accuracy and performance during aspect-based sentiment analysis. The objective of this research is to present a detailed review and comparative analysis of machine learning and deep learning approaches in aspect-based sentiment analysis.

Sentiment analysis or opinion mining used to capture the community's attitude who have experienced the specific service/product. Sentiment analysis usually concentrates to classify the opinion of whole document or sentence. However, in most comments, users often express their opinions on different aspects of the mentioned entity rather than express general sentiments on entire document. In this case, using aspect-based sentiment analysis (ABSA) is a solution. ABSA emphases on extracting and synthesizing sentiments on particular aspects of entities in opinion text. The previous studies have difficulty working with aspect extraction and sentiment polarity classification in multiple domains of review. We offer an innovative deep learning approach with the integrated construction of bidirectional Long Short Term Memory (BiLSTM) and Convolutional Neural Network (CNN) for multidomain ABSA in this article. Our system finished the following tasks: domain classification, aspect extraction and opinion determination of aspect in the document. Besides applying GloVe word embedding for input sentences from mixed Laptop_Restaurant domain of the SemEval 2016 dataset, we also use the additional layer of POS to pick out the word morphological attributes before feeding to the CNN_BiLSTM architecture to enhance the flexibility and precision of our suggested model. Through experiment, we found that our proposed model has performed the above mentioned tasks of domain classification, aspect and sentiment extraction concurrently on a mixed domain dataset and achieved the positive results compared to previous models that were performed only on separated domain dataset.