Sentiment Sentences Research Articles

Sentence level Classification through machine learning with effective feature extraction using deep learning

Social networking website usage has increased dramatically during the past few years. Users can read other users' views, which are categorized into several sentiment classes on this medium with an array of data. These opinions are becoming more and more important while making decisions. To address the above-mentioned issues and improve the sentence-level classification's classification rate, this work introduces a new extensive pinball loss function based twin support vector machine with Deep Learning the (EPLF-TSVM-DL) to identify the polarity (negative and positive) of sentiment sentences. There are four primary components of this technique: The first portion consists of pre-processing the data to minimize noise and improve quality; the second part utilizes word embedding techniques to transform textual data into numerical data. The third part is the CNN for an efficient automatic method of extracting the features-based feature extraction and final is EPLF-TSVM-DL is used for sentence level classification that forms two classes such as Negative and Positive. The findings demonstrated that the EPLF-TSVM-DL outperforms the other classifiers with respect to of time consumption, convergence, complexity, and stability as well as true negative, true positive, error rate, false positive, precision, false negative, and classification rate.

An Empirical Evaluation of Adapting Hybrid Parameters for CNN-based Sentiment Analysis

Sentiment analysis aims to understand human emotions and perceptions through various machine-learning pipelines. However, feature engineering and inherent semantic gap constraints often hinder conventional machine learning techniques and limit their accuracy. Newer neural network models have been proposed to automate the feature learning process and enrich learned features with word contextual embeddings to identify their semantic orientations to address these challenges. This article aims to analyze the influence of different factors on the accuracy of sentiment classification predictions by employing Feedforward and Convolutional Neural Networks. To assess the performance of these neural network models, we utilize four diverse real-world datasets, namely 50,000 movie reviews from IMDB, 10,662 sentences from LightSide Movie_Reviews, 300 public movie reviews, and 1,600,000 tweets extracted from Sentiment140. We experimentally investigate the impact of exploiting GloVe word embeddings on enriching feature vectors extracted from sentiment sentences. Findings indicate that using larger dimensions of GloVe word embeddings increases the sentiment classification accuracy. In particular, results demonstrate that the accuracy of the CNN with a larger feature map, a smaller filter window, and the ReLU activation function in the convolutional layer was 90.56% using the IMDB dataset. In comparison, it was 80.73% and 77.64% using the sentiment140 and the 300 sentiment sentences dataset, respectively. However, it is worth mentioning that, with large-size sentiment sentences (LightSide’s Movie Reviews) and using the same parameters, only a 64.44% level of accuracy was achieved.

Sentiment Analysis of Sentence-Level using Dependency Embedding and Pre-trained BERT Model

Sentiment analysis is a valuable field of research in NLP with many applications. Dependency tree is one of the language features that can be utilized in this field. Dependency embedding, as one of the semantic representations of a sentence, has shown to provide more significant results compared to other embeddings, which makes it a potential way to improve the performance of sentiment analysis tasks. This study aimed to investigate the effect of dependency embedding on sentence-level sentiment analysis through experimental research. The study replaced the Vocabulary Graph embedding in the VGCN-BERT sentiment classification system architecture with several dependency embedding representations, including word vector, context vector, average of word and context vectors, weighting on word and context vectors, and merging of word and context vectors. The experiments were conducted on two datasets, SST-2 and CoLA, with more than 19 thousand labeled sentiment sentences. The results indicated that dependency embedding can enhance the performance of sentiment analysis at the sentence level.

Neural Network-Based Sentiment Classification of Russian Sentences into Four Classes

The paper is devoted to the classification of Russian sentences into four classes: positive, negative, mixed, and neutral. Unlike the majority of modern study in this area, the mixed sentiment class is introduced. Mixed sentiment sentences contain positive and negative sentiments simultaneously.To solve the problem, the following tools were applied: the attention-based LSTM neural network, the dual attention-based GRU neural network, the BERT neural network with several modifications of the output layer to provide classification into four classes. The experimental comparison of the efficiency of various neural networks were performed on three corpora of Russian sentences. Two of them consist of users’ reviews: one with wear reviews and another with hotel reviews. The third corpus contains news from Russian media. The highest weighted F-measure in experiments (0.90) was achieved when using BERT on the wear reviews corpus, as well as the highest weighted F-measure for positive and negative sentences (0.92 and 0.93, respectively). The best classification results for neutral and mixed sentences were achieved on the news corpus. For them F-measure was 0.72 and 0.58, respectively. As a result of experiments, the significant superiority of the BERT transfer network was demonstrated in comparison with older neural networks LTSM and GRU, especially for classification of sentences with weakly expressed sentiments. The error analysis showed that “adjacent” (positive/negative and mixed) classes are worse classified with BERT than “opposite” classes (positive and negative, neutral and mixed).

Aspect Based Sentiment Analysis

Sentiment analysis, which addresses the computational treatment of opinion, sentiment, and subjectivity in text, has received considerable attention in recent years. In contrast to the traditional coarse-grained sentiment analysis tasks, such as document-level sentiment classification, we are interested in the fine-grained aspect-based sentiment analysis that aims to identify aspects that users comment on and these aspects’ polarities. Aspect-based sentiment analysis relies heavily on syntactic features. However, the reviews that this task focuses on are natural and spontaneous, thus posing a challenge to syntactic parsers. In this paper, we address this problem by proposing a framework of adding a sentiment sentence compression (Sent Comp) step before performing the aspect-based sentiment analysis. We apply a discriminative conditional random field model, with certain special features, to automatically compress sentiment sentences. Sentiment analysis is contextual mining of text which identifies and extracts subjective information in textual data. sentiment analysis proves to be an incredible asset for users to extract essential information and assists organizations with understanding the social sentiment of their brand, product or service while monitoring online conversations.

A novel scheme of domain transfer in document-level cross-domain sentiment classification

The sentiment classification aims to learn sentiment features from the annotated corpus and automatically predict the sentiment polarity of new sentiment text. However, people have different ways of expressing feelings in different domains. Thus, there are important differences in the characteristics of sentimental distribution across different domains. At the same time, in certain specific domains, due to the high cost of corpus collection, there is no annotated corpus available for the classification of sentiment. Therefore, it is necessary to leverage or reuse existing annotated corpus for training. In this article, we proposed a new algorithm for extracting central sentiment sentences in product reviews, and improved the pre-trained language model Bidirectional Encoder Representations from Transformers (BERT) to achieve the domain transfer for cross-domain sentiment classification. We used various pre-training language models to prove the effectiveness of the newly proposed joint algorithm for text-ranking and emotional words extraction, and utilised Amazon product reviews data set to demonstrate the effectiveness of our proposed domain-transfer framework. The experimental results of 12 different cross-domain pairs showed that the new cross-domain classification method was significantly better than several popular cross-domain sentiment classification methods.

Analisis Sentimen Masyarakat Terhadap Kinerja Persatuan Sepakbola Seluruh Indonesia Menggunakan Metode Backpropagation

Sentiment analysis in a sentence describes the part of the consideration of an entity or a event regarding the product, service, topic, issue, person, organization, or event that becomes the target object in sentiment sentences. Judging from several reasons for positive and negative sentiments originating from social media, researchers will use social media not only to communicate between friends, but will be used as a means to find out an aspiration for the community, especially the Indonesian community regarding legal issues or problems related to government. One of the aspirations that will be analyzed is the performance of PSSI. In analyzing this, researchers using the Backpropagation Method are learning methods to reduce error rates by adjusting their weight based on the desired output and target differences. Backpropagation is also a systematic method for multilayer training in Artificial Neural Networks. Backpopagation is said to be a multilayer training method because Backpropagation has three layers in the training process, namely input layer, hidden layer and output layer

Identification of fact-implied implicit sentiment based on multi-level semantic fused representation

Sentiment can be expressed in an explicit or implicit manner. Most of the current studies on sentiment analysis focus on the identification of explicit sentiment but ignore the implicit. According to our statistics during data labeling in previous work, nearly a third of subjective sentences contain implicit sentiment, and 72% of the implicit sentiment sentences are fact-implied ones. We analyze the characteristics of the sentences that express fact-implied implicit sentiment and consider that fact-implied implicit sentiment is usually affected by its sentiment target, context semantic background and its own sentence structure. This paper focuses on the recognition of fact-implied implicit sentiment at the sentence level. A multi-level semantic fusion method is proposed to learn the features for identification based on representation learning. Three features in different levels are learned from the corpus, namely, sentiment target representation at the word level, structure embedded representation at the sentence level and context semantic background representation at the document level. We manually construct a fact-implied implicit sentiment corpus in Chinese, and experiments on the datasets show that the proposed method can effectively recognize fact-implied implicit sentiment sentences.

Sentence Compression for Aspect-Based Sentiment Analysis

Sentiment analysis, which addresses the computational treatment of opinion, sentiment, and subjectivity in text, has received considerable attention in recent years. In contrast to the traditional coarse-grained sentiment analysis tasks, such as document-level sentiment classification, we are interested in the fine-grained aspect-based sentiment analysis that aims to identify aspects that users comment on and these aspects' polarities. Aspect-based sentiment analysis relies heavily on syntactic features. However, the reviews that this task focuses on are natural and spontaneous, thus posing a challenge to syntactic parsers. In this paper, we address this problem by proposing a framework of adding a sentiment sentence compression (Sent_Comp) step before performing the aspect-based sentiment analysis. Different from the previous sentence compression model for common news sentences, Sent_Comp seeks to remove the sentiment-unnecessary information for sentiment analysis, thereby compressing a complicated sentiment sentence into one that is shorter and easier to parse. We apply a discriminative conditional random field model, with certain special features, to automatically compress sentiment sentences. Using the Chinese corpora of four product domains, Sent_Comp significantly improves the performance of the aspect-based sentiment analysis. The features proposed for Sent_Comp, especially the potential semantic features, are useful for sentiment sentence compression.

영화평과 평점을 이용한 감성 문장 구축을 통한 영화 평점 추론

영화 리뷰 사이트에서 영화 평점은 네티즌들의 주관적 판단으로 결정된다. 이로 인해 그들이 남긴 영화평과 평점 사이의 극성이 서로 불일치하는 경우가 종종 발생한다. 본 논문에서는 이 문제를 해결하기 위해 영화의 평가에 영향을 미치는 감성 문장들의 집합을 만들고, 이들을 영화평에 적용하여 평점을 추론한다. 감성 문장들의 집합을 만들기 위한 과정은 감성 어휘 사전을 구축하는 단계와 감성 문장을 구성하는 단계로 이루어진다. 감성 어휘 사전은 영화평에서 쓰인 형용사와 형용사의 극성을 저장한다. 감성 문장은 영화와 관련된 명사를 주어로 갖고 감성 어휘 사전의 어휘를 서술어로 갖는 문장 구조이다. 감성 문장의 극성과 감성 문장에서 쓰인 서술어의 극성이 다른 문장들은 제거하여 감성 문장들이 감성 어휘 사전 어휘의 극성과 일치되도록 하였다. 영화평에서 쓰인 감성 문장들의 평균 점수를 구하면 영화평이 갖는 감성 점수가 된다. 본 연구 결과를 통해 네티즌들이 매긴 평점에 비해 감성 문장 집합을 적용하여 계산한 영화평의 감성 점수가 영화평에 대한 의견을 더 잘 반영한다는 것을 알 수 있다. On movie review sites, movie ratings are determined by netizens' subjective judgement. This means that inconsistency between ratings and opinions from netizens often occurs. To solve this problem, this paper proposes sentiment sentence sets which affect movie evaluation, and apply sets to comments to infer ratings. Creation of sentiment sentence sets is consisted of two stages, construction of sentiment word dictionary and creation of sentiment sentences for sentiment estimation. Sentiment word dictionary contains sentimental words and its polarities included in reviews. Elements of sentiment sentences are combined with movie related noun and predicate from words sentiment word dictionary. In this study, to make correspondence between polarity of sentiment sentence and sentiment word dictionary, sentiment sentences which have different polarity with sentiment word dictionary are removed. The scores of comments are calculated by applying averages of sentiment sentences elements. The result of experiment shows that sentence scores from sentiment sentence sets are closer to reflect real opinion of comments than ratings by netizens'.

스탠포드 감성 트리 말뭉치를 이용한 감성 분류 시스템

The main goal of this research is to build a sentiment analysis system which automatically determines user opinions of the Stanford Sentiment Treebank in terms of three sentiments such as positive, negative, and neutral. Firstly, sentiment sentences are POS tagged and parsed to dependency structures. All nodes of the Treebank and their polarities are automatically extracted from the Treebank. We train two Support Vector Machines models. One is for a node level classification and the other is for a sentence level. We have tried various type of features such as word lexicons, POS tags, Sentiment lexicons, head-modifier relations, and sibling relations. Though we acquired 74.2% in accuracy on the test set for 3 class node level classification and 67.0% for 3 class sentence level classification, our experimental results for 2 class classification are comparable to those of the state of art system using the same corpus.

Aspect Identification of Sentiment Sentences Using A Clustering Algorithm

Reviews contain aspect information of a product, such as “image quality” and “usability” of a camera. In this paper, we propose an aspect identification method for sentiment sentences in review documents. Machine learning methods usually require a large amount of training data for generating a classifier with high accuracy. However, preparing training data by hand is costly. To solve this problem, we apply a clustering approach to the aspect identification method. Our system acquires new training data from non-tagged data by using the clustering approach. As compared with a baseline method, which does not use the acquisition approach, our method obtained high accuracy.