Sentiment analysis via semi-supervised learning: a model based on dynamic threshold and multi-classifiers

Han, Yue; Liu, Yuhong; Zhang, Jin

doi:10.1007/s00521-018-3958-3

Cited by 25 publications

(27 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The traditional methods for sentiment classification include lexicons or using dictionaries for labelling the data sets, followed by supervised learning. The drawbacks of these oldfashioned techniques comprise labelling a full set of data, which is expensive (Han et al, 2019). Moreover, the lexicons can only label limited words and cannot keep up with the new slangs, sentiment bearing words and other special words.…”

Section: Related Workmentioning

confidence: 99%

“…One popular way to extract information and gain insight into consumer opinion is sentiment analysis. Sentiment analysis has become increasingly popular because of open challenges, new application areas and outstanding benefits in marketing, political campaigns, election monitoring, financial predictions and other important tasks (Han et al, 2019). It can be performed at various levels of granularities, one of the recently popularized methods being: aspect-based sentiment analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Aspect context aware sentiment classification of online consumer reviews

Bansal

Srivastava

2020

IDD

View full text Add to dashboard Cite

Purpose Aspect based sentiment classification is valuable for providing deeper insight into online consumer reviews (OCR). However, the majority of the previous studies explicitly determine the orientation of aspect related sentiment bearing word and overlook the aspect-context. Therefore, this paper aims to propose an aspect-context aware sentiment classification of OCR for deeper and more accurate insights. Design/methodology/approach In the proposed methodology, first, aspect descriptions and sentiment bearing words are extracted. Then, the skip-gram model is used to extract the first set of features to capture contextual information. For the second category of features, cosine similarity is used between a pre-defined seed word list and aspects, to capture aspect context sensitive sentiments. The third set of features includes weighted word vectors using term frequency-inverse document frequency. After concatenating features, ensemble classifier is used using three base classifiers. Findings Experimental results on two real-world data sets with variable lengths, acquired from Amazon.com and TripAdvisor.com, show that the advised ensemble approach significantly outperforms sentiment classification accuracy of state-of-the-art and baseline methods. Originality/value This method is capable of capturing the correct sentiment of ambiguous words and other special words by extracting aspect-context using word vector similarity instead of expensive lexical resources, and hence, shows superior performance in terms of accuracy as compared to other methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Aspect context aware sentiment classification of online consumer reviews

Bansal

Srivastava

2020

IDD

View full text Add to dashboard Cite

show abstract

“…Analysis and Discussion Table (2) summarize all proposed techniques, dataset used, problems that system solve, evaluation and limitation. [38,42]…”

Section: -Corpus-based Approachmentioning

confidence: 99%

A survey on Sentimental Analysis algorithms and techniques

2020

Journal of the ACS Advances in Computer Science

View full text Add to dashboard Cite

Abstract-Social web has been the lead of data in recent years. The data on social web simulates the customer reviews, comments, and opinions of people about products, opinion, events, etc. The automatic mining technique that is used to gather and analyze text and classify it into positive, negative and neutral is called Sentimental analysis using Natural language processing. The main objective of this paper is to give explain insights on SA algorithms and techniques.

show abstract

“…Therefore, the scaling of supervised approaches to multiple domains is difficult. Labeled data scarcity is overcome by recent semisupervised approaches that include combining labeled and unlabeled data [19], self-training [20], co-training [21], and sentiment topic-model [22] approaches. An unsupervised approach overcomes the absence of labeled data with a knowledge graph propagation approach using a sentiment lexicon [41].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Genre-Based Multidomain Sentiment Lexicon Learning Using Corpus-Generated Polarity Seed Words

Sanagar

Gupta

2020

IEEE Access

View full text Add to dashboard Cite

Sentiment lexicon learning is of paramount importance in sentiment analysis. One of the most considerable challenges in learning sentiment lexicons is their domain-specific behavior. Transferring knowledge acquired from a sentiment lexicon from one domain to another is an open research problem. In this study, we attempt to address this challenge by presenting a transfer learning approach that creates new learning insights for multiple domains of the same genre. We propose an unsupervised sentiment lexicon learning methodology scalable to new domains of the same genre. Incremental learning and the methodology learn polarity seed words from corpora of multiple automatically selected source domains. This process then transfers its genre-level knowledge of corpus-learned seed words to the target domains. The corpus-learned seed words are used for sentiment lexicon generation for multiple target domains of the same genre. The sentiment lexicon learning process is based on the latent semantic analysis technique and uses unlabeled training data from the source and target domains. The experiment was performed using 24 domains of the same genre, i.e., consumer product review. The proposed model displays the best results using standard evaluation measures compared with the competitive baselines. The proposed genre-based unsupervised approach achieves a maximum accuracy of 86% and outperforms methods recently presented in the literature.

show abstract

Sentiment analysis via semi-supervised learning: a model based on dynamic threshold and multi-classifiers

Cited by 25 publications

References 25 publications

Aspect context aware sentiment classification of online consumer reviews

Aspect context aware sentiment classification of online consumer reviews

A survey on Sentimental Analysis algorithms and techniques

Unsupervised Genre-Based Multidomain Sentiment Lexicon Learning Using Corpus-Generated Polarity Seed Words

Contact Info

Product

Resources

About