TASCI: transformers for aspect-based sentiment analysis with contextual intent integration.

In the expanding field of sentiment analysis, the integration of personality prediction into aspect-based sentiment analysis (ABSA) represents a novel and promising approach to enhance the accuracy and depth of sentiment detection. This paper proposes a unique framework that leverages the Big Five personality traits (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) alongside Long Short-Term Memory (LSTM) networks, under a multitask learning paradigm, to improve the performance of ABSA. This is, to the best of knowledge, the first work considering the use of personality traits as auxiliary tasks in order to capture the manifold subtle ways in which personality would influence the expression of sentiment towards the different aspects of products or services. And then, model uses the LSTM component to model the sequential character of the text, which makes the extraction accurate in terms of the aspect terms and sentiment polarities. The proposed model designs a multitask learning strategy simultaneously to predict sentiments and personality traits. Such joint learning will allow enhancing the model's understanding of textual context and sentiment expression. Thorough experiments on many benchmark datasets show that the proposed approach is competitive with the state of the art for the aspect-based sentiment analysis and provides some of the deepest insights into personality predictions. Model has obtained F1-scores of 79.78%, 83.67%, and 88.80 % on the Twitter, Laptop, and Restaurant datasets, respectively. These results highlight a significant improvement over existing methods in the literature. For instance, our model outperformed traditional approaches like RAM, which achieved 69.36% on the Twitter dataset, and even advanced techniques such as DualGCN+Bert, which scored 77.4% on Twitter. It can be generally concluded that this research finally opens the way to a new and meaningful opportunity for sentiment analysis applications: integrated into ABSA models, personality prediction advances applications ranging from personalized recommendation systems to the nuance market analysis tools. As far as we know this study is the first attempt to utilise personality feature to enhance sentiment prediction tasks.

The domain of Aspect Level Sentiment Classification, in which the sentiment toward a given aspect is analyzed, attracts much attention in NLP. Recently, the state-of-the-art Aspect Level Sentiment Classification methods are devised by using the Graph Convolutional Networks to deal with both the semantics and the syntax of the sentence. Generally, the parsing of syntactic structure inevitably incorporates irrelevant information toward the aspect. Besides, the syntactic and semantic alignment and uniformity that contribute to the sentiment delivery is currently neglected during processing. In this work, a Triplet Contrastive Learning Network is developed to coordinate the syntactic information and the semantic information. To start with, the aspect-oriented sub-tree is constructed to replace the syntactic adjacency matrix. Further, a sentence-level contrastive learning scheme is proposed to highlight the features of sentiment words. Based on The Triple Contrastive Learning, the syntactic information and the semantic information are thoroughly interacted and coordinated whilst the global semantics and syntax can be exploited. Extensive experiments are performed on three benchmark datasets and achieve accuracies (BERT-based) of 87.40, 82.80, 77.55 on Rest14, Lap14, and Twitter datasets, which demonstrate that our approach achieves state-of-the-art results in Aspect Level Sentiment Classification task.

Aspect sentiment learning for Aspect-Level Sentiment Classification.

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.

Aspect-level sentiment classification aims to determine sentiment polarities of various aspects in reviews, where each review typically contains multiple aspects, that may correspond to different polarities. Aspect-level sentiment classification, unlike document-level sentiment classification, requires different context representations for different aspects. Existing methods normally use Long Short-Term Memory (LSTM) network to model aspects and contexts separately, and they combine attention mechanisms to extract features of a specific aspect in its context. Attention mechanisms are not used for sequence modeling, so aspects are not considered when generating context sequence representations. This study proposes a novel aspect-context interactive representation structure that only relies on an attention mechanism for generating sequence-to-sequence representations in both context and aspect. It is capable of extracting features related to the specific aspect during the process of its context sequence modeling, and generating a high quality aspect representation simultaneously. We have conducted comprehensive experiments to compare with thirteen existing methods. Our experimental results show that the proposed model is able to achieve significantly better performance on Restaurant dataset, as well as very competitive results on Laptop and Twitter datasets.

Aspect-level sentiment classification is a fine-grained sentiment analysis task, which aims to predict the sentiment of a text in different aspects. One key point of this task is to allocate the appropriate sentiment words for the given aspect.Recent work exploits attention neural networks to allocate sentiment words and achieves the state-of-the-art performance. However, the prior work only attends to the sentiment information and ignores the aspect-related information in the text, which may cause mismatching between the sentiment words and the aspects when an unrelated sentiment word is semantically meaningful for the given aspect. To solve this problem, we propose a HiErarchical ATtention (HEAT) network for aspect-level sentiment classification. The HEAT network contains a hierarchical attention module, consisting of aspect attention and sentiment attention. The aspect attention extracts the aspect-related information to guide the sentiment attention to better allocate aspect-specific sentiment words of the text. Moreover, the HEAT network supports to extract the aspect terms together with aspect-level sentiment classification by introducing the Bernoulli attention mechanism. To verify the proposed method, we conduct experiments on restaurant and laptop review data sets from SemEval at both the sentence level and the review level. The experimental results show that our model better allocates appropriate sentiment expressions for a given aspect benefiting from the guidance of aspect terms. Moreover, our method achieves better performance on aspect-level sentiment classification than state-of-the-art models.

Aspect-based sentiment classification (ABSC) (also called fine-grained sentiment analysis) is an essential and challenging task among sentiment analysis tasks. Aspect level sentiment analysis overcomes the limitation of the document and sentence level when multiple aspects appear in a review. Recently, neural network approaches like LSTM has achieved better results in ABSC than traditional machine learning algorithms. Aspect extraction and polarity detection for specific aspects in the review becoming an important task in aspect level sentiment analysis. Therefore, the paper aims to predict the sentiment polarity of each aspect in the review into 3 classes by developing the multi-aspect attention (MAA) model and combine it with the BiLSTM neural network, called MAA-BLSTM. Unlike unidirectional LSTM, the BiLSTM network runs the input in two directions: forward and backward, therefore, it can understand the context better than LSTM. In this paper, the hyperparameter tuning approach is also considered to be the high-performing model. Experiments are tested on restaurant and laptop data from SemEval (2014, 2015, and 2016) datasets and compare the result with other LSTM-based methods. Finally, the result proves that the accuracy of the proposed sentiment model reaches 89.9 on the restaurant dataset and 82.1 on the laptop dataset which are higher than other LSTM approaches.

Aspect-level sentiment classification (ASC) is a fine-grained sentiment analysis task that involves detecting the sentiment polarity of a specific opinion target in a given sentence. Despite the popularity of deep learning methods, the limited availability of ASC training data has resulted in the suboptimal performance of neural network models. To address this issue, researchers have proposed transferring resource-rich document-level sentiment knowledge to ASC tasks using model transfer and shared parameters. However, these methods have neglected the impact of differences in the training data for different tasks on the shared layer parameters. Therefore, this paper proposes a transfer method that automatically adapts to task and domain differences—Auto-adaptive Model Transfer (AAMT). This method considers adding specific disturbance variables on shared layer parameters to subdivide task differences to further obtain more accurate and effective transfer knowledge. In addition, on this basis, we introduce an attention mechanism to combine aspect and sentence features to better capture the sentiment vocabulary associated with a given target. A series of experiments on three public datasets show that our proposed method can solve the problem of insufficient training data for ASC and achieve good results.

SK-GCN: Modeling Syntax and Knowledge via Graph Convolutional Network for aspect-level sentiment classification

Integrating color cues to improve multimodal sentiment analysis in social media

In this paper, the focus is on sentiment analysis of web 3.0 enabled twitter dataset. The objective of the project is to explore various methods for performing sentiment analysis on Twitter datasets and implementing these methods on the web3.0 Twitter platform. The project involves collecting Twitter data through blockchain-based applications, preprocessing the data to remove noise, and applying machine learning models for sentiment analysis. Sentiment analysis is simply the extraction of thoughts, ideas, opinions, and emotions from sources such as text, speech, tweets, and databases using natural language processing (NLP) This process involves text segmentation mentally makes it "good," "bad," and "neutral" groups. In addition, it is known by other terms such as objective evaluation, mindfulness mining, and rating extraction. Web 3.0, also known as Web3, represents the third contemplated iteration of the World Wide Web, which aspires to establish a connected, transparent and intelligent online environment Based on the concept of decentralization, blockchain technology and the implementation of token-based economies. The main outcome of the project is to gain insights into the sentiment of users by analyzing WEB3.0 enabled Twitter data. By implementing sentiment analysis techniques on a WEB3.0 enabled Twitter dataset, the project aims to contribute to the field of sentiment analysis and showcase the effectiveness of using WEB3.0 enabled for data collection and analysis. The project aims to provide valuable insights for various methods of sentiment analysis for researchers. Keywords – Sentiment Analysis, Blockchain- Enabled, Twitter data, WEB 3.0, Machine Learning Models, User Sentiment, Research Contribution

Twitter sentiment analysis using hybrid cuckoo search method

Aspect level sentiment classification aims to recognize the sentiment polarity of each aspect term in a sentence. However, most of the existing methods usually applied the attention mechanism over position-weighted memory and did not consider inter-aspect information. To address these issues, we propose a novel framework for aspect level sentiment classification, Deep Selective Memory Network (DSMN), which selects the context memory dynamically for better guiding the multi-hop attention mechanism and integrates inter-aspect information with deep memory network. By designing a selective attention mechanism based on the distance information between an aspect and its context, DSMN focuses on different parts of the context memory in different memory network layers to capture abundant aspect-aware context information. Besides, to make full use of the inter-aspect information, we also design effective inter-aspect modeling modules to generate both semantic and relation information of the nearby aspects for the desired aspect. We evaluate the advantages of our framework on three benchmark datasets, and experiment results show that our framework achieves state-of-the-art performance.

Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. To address this problem, recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree that can locate the opinion words. However, the induced opinion words only provide an intuitive cue far below human-level interpretability. Besides, the pre-trained encoder tends to internalize an aspect's intrinsic sentiment, causing sentiment bias and thus affecting model performance. In this paper, we propose a span-based anti-bias aspect representation learning framework. It first eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects' prior sentiment. Then, it aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms. Our method achieves new state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.

This study aims to define sentiment expressions from the perspective of Korean linguistics and present the research process for extracting sentiment expressions in Korean product reviews. For the purpose of this study, an 8 million word clothing corpus was built; this was composed of product reviews, online magazines and professional fashion blogs, which have been morphologically annotated. Chapter 2 presents the corpus-driven methodology adopted for the research process, which focuses on n-gram and POS-gram analysis. Chapter 3 addresses issues regarding the pre-processing procedure and the establishment of the list of candidate sentiment expressions at word and phrase level. Chapter 4 deals with issues concerning phrase level analysis and discusses the correlation between sentiment analysis in domain-specific genres and the notion of ‘semantic unit’ as defined in corpus linguistics.