Context-sensitive and attribute-based sentiment classification of online consumer-generated content

Kybernetes ◽  
2019 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Barkha Bansal ◽  
Sangeet Srivastava
Keyword(s):  
Latent Dirichlet Allocation ◽  
Brand Management ◽  
Sentiment Classification ◽  
Practical Significance ◽  
Sensitive Information ◽  
Content Type ◽  
Context Sensitive ◽  
Online Consumer ◽  
Product Improvement

Purpose Vast volumes of rich online consumer-generated content (CGC) can be used effectively to gain important insights for decision-making, product improvement and brand management. Recently, many studies have proposed semi-supervised aspect-based sentiment classification of unstructured CGC. However, most of the existing CGC mining methods rely on explicitly detecting aspect-based sentiments and overlooking the context of sentiment-bearing words. Therefore, this study aims to extract implicit context-sensitive sentiment, and handle slangs, ambiguous, informal and special words used in CGC. Design/methodology/approach A novel text mining framework is proposed to detect and evaluate implicit semantic word relations and context. First, POS (part of speech) tagging is used for detecting aspect descriptions and sentiment-bearing words. Then, LDA (latent Dirichlet allocation) is used to group similar aspects together and to form an attribute. Semantically and contextually similar words are found using the skip-gram model for distributed word vectorisation. Finally, to find context-sensitive sentiment of each attribute, cosine similarity is used along with a set of positive and negative seed words. Findings Experimental results using more than 400,000 Amazon mobile phone reviews showed that the proposed method efficiently found product attributes and corresponding context-aware sentiments. This method also outperforms the classification accuracy of the baseline model and state-of-the-art techniques using context-sensitive information on data sets from two different domains. Practical implications Extracted attributes can be easily classified into consumer issues and brand merits. A brand-based comparative study is presented to demonstrate the practical significance of the proposed approach. Originality/value This paper presents a novel method for context-sensitive attribute-based sentiment analysis of CGC, which is useful for both brand and product improvement.

Aspect context aware sentiment classification of online consumer reviews

2020 ◽  
Vol 48 (3) ◽  
pp. 117-128
Author(s):  
Barkha Bansal ◽  
Sangeet Srivastava
Keyword(s):  
Sentiment Classification ◽  
Superior Performance ◽  
Context Aware ◽  
Lexical Resources ◽  
Real World Data ◽  
Consumer Reviews ◽  
Content Type ◽  
Online Consumer Reviews ◽  
Online Consumer

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.

scholarly journals Application of Latent Dirichlet Allocation (LDA) for clustering financial tweets

2021 ◽  
Vol 297 ◽  
pp. 01071
Author(s):  
Sifi Fatima-Zahrae ◽  
Sabbar Wafae ◽  
El Mzabi Amal
Keyword(s):  
Language Processing ◽  
Latent Dirichlet Allocation ◽  
Sentiment Classification ◽  
Research Areas ◽  
Preprocessing Method ◽  
Long Time ◽  
Standard Text ◽  
The Given ◽  
Dirichlet Allocation

Sentiment classification is one of the hottest research areas among the Natural Language Processing (NLP) topics. While it aims to detect sentiment polarity and classification of the given opinion, requires a large number of aspect extractions. However, extracting aspect takes human effort and long time. To reduce this, Latent Dirichlet Allocation (LDA) method have come out recently to deal with this issue.In this paper, an efficient preprocessing method for sentiment classification is presented and will be used for analyzing user’s comments on Twitter social network. For this purpose, different text preprocessing techniques have been used on the dataset to achieve an acceptable standard text. Latent Dirichlet Allocation has been applied on the obtained data after this fast and accurate preprocessing phase. The implementation of different sentiment analysis methods and the results of these implementations have been compared and evaluated. The experimental results show that the combined uses of the preprocessing method of this paper and Latent Dirichlet Allocation have an acceptable results compared to other basic methods.

Sentiment classification of Chinese cosmetic reviews based on integration of collocations and concepts

2019 ◽  
Vol 38 (1) ◽  
pp. 155-169
Author(s):  
Chihli Hung ◽  
You-Xin Cao
Keyword(s):  
Design Methodology ◽  
Classification Performance ◽  
Sentiment Classification ◽  
Support Vector ◽  
Research Approach ◽  
Content Type ◽  
Novel Approach ◽  
The Relationship ◽  
Modelling Approach

Purpose This paper aims to propose a novel approach which integrates collocations and domain concepts for Chinese cosmetic word of mouth (WOM) sentiment classification. Most sentiment analysis works by collecting sentiment scores from each unigram or bigram. However, not every unigram or bigram in a WOM document contains sentiments. Chinese collocations consist of the main sentiments of WOM. This paper reduces the complexity of the document dimensionality and makes an improvement for sentiment classification. Design/methodology/approach This paper builds two contextual lexicons for feature words and sentiment words, respectively. Based on these contextual lexicons, this paper uses the techniques of associated rules and mutual information to build possible Chinese collocation sets. This paper applies preference vector modelling as the vector representation approach to catch the relationship between Chinese collocations and their associated concepts. Findings This paper compares the proposed preference vector models with benchmarks, using three classification techniques (i.e. support vector machine, J48 decision tree and multilayer perceptron). According to the experimental results, the proposed models outperform all benchmarks evaluated by the criterion of accuracy. Originality/value This paper focuses on Chinese collocations and proposes a novel research approach for sentiment classification. The Chinese collocations used in this paper are adaptable to the content and domains. Finally, this paper integrates collocations with the preference vector modelling approach, which not only achieves a better sentiment classification performance for Chinese WOM documents but also avoids the curse of dimensionality.

scholarly journals Exploring online consumer curation as user-generated content

2019 ◽  
Vol 23 (3) ◽  
pp. 325-338 ◽  
Author(s):  
Jessica Babin ◽  
John Hulland
Keyword(s):  
Brand Management ◽  
User Generated Content ◽  
Social Connections ◽  
Future Research ◽  
Careful Study ◽  
Art Gallery ◽  
Content Type ◽  
Academic Literature ◽  
Online Consumer ◽  
Practical Implications

Purpose Some consumers are engaged in online curation, a type of user-generated content, in ways that can be impactful for brands. An example of online curation includes organizing themed collections of product images on Pinterest. The purpose of this paper is to present a framework of online consumer curation, introducing this topic to the marketing literature. Design/methodology/approach Through the analysis of the business and academic literature, as well as a careful study of many examples of online consumer curation, the authors present a framework for understanding online consumer curation. Findings The actions taken by online consumer curators are similar to those of museum or art gallery curators: acquiring, selecting, organizing and displaying content for an audience. The motivations for consumers to engage in online curation include building/displaying their identities and making social connections with their online audience. One outcome possible for the audience that views the curation is gaining access to carefully selected and recommended content. Research limitations/implications As online consumer curation is a new area of research, the authors suggest several marketing- and brand-relevant propositions that can be addressed in future research. Practical implications As consumers are frequently using product images and brand symbols in their online curation, it is important for marketing academics and practitioners to understand their actions. Originality/value The aim of the paper is to present a thorough introduction to the idea of online consumer curation by outlining relevant examples, providing a framework for understanding this activity and its implications for brand management, and listing ideas for future research.

Brand management and the world of the arts: collaboration, co-operation, co-creation, and inspiration

2018 ◽  
Vol 27 (3) ◽  
pp. 237-248 ◽  
Author(s):  
Carsten Baumgarth
Keyword(s):  
Brand Management ◽  
Future Research ◽  
Special Issue ◽  
Content Type ◽  
The Past ◽  
The Arts ◽  
Four Levels ◽  
Key Aspects ◽  
Published Research

Purpose This paper aims to present historical examples of collaborations between brand strategists and artists; provide an extensive, structured overview of existing published research on such collaborations and their effects; present seven papers comprising this special issue; and discuss ideas for further research into brand–art collaboration. Design/methodology/approach This is an editorial based mainly on an extensive and broad literature review. Findings First, this editorial underpins the relevance of brand–art collaboration in the past and present by reference to real examples. Second, it structures the diverse literature into four key aspects of the topic: inspiration, insights, identity and image. Third, it provides a glimpse of the seven papers selected for this special issue. Fourth and finally, it identifies a total of 16 avenues for further research, on four levels (artist, brand owner, consumer and cooperation process). Originality/value This editorial and the entire special issue together represent the first anthology on the topic of the interface between brand management and arts. The collection and classification of the existing literature, the formulation of ideas for future research and the content of the seven papers are collectively excellent starting springboards for new and fresh brand research projects.

Multi-class Twitter sentiment classification with emojis

2018 ◽  
Vol 118 (9) ◽  
pp. 1804-1820 ◽  
Author(s):  
Mengdi Li ◽  
Eugene Ch’ng ◽  
Alain Yee Loong Chong ◽  
Simon See
Keyword(s):  
Sentiment Analysis ◽  
Sentiment Classification ◽  
Training Data ◽  
Data Set ◽  
Content Type ◽  
Terror Attacks ◽  
Processing Techniques ◽  
Political Opinions ◽  
Training Sets

Purpose Recently, various Twitter Sentiment Analysis (TSA) techniques have been developed, but little has paid attention to the microblogging feature – emojis, and few works have been conducted on the multi-class sentiment analysis of tweets. The purpose of this paper is to consider the popularity of emojis on Twitter and investigate the feasibility of an emoji training heuristic for multi-class sentiment classification of tweets. Tweets from the “2016 Orlando nightclub shooting” were used as a source of study. Besides, this study also aims to demonstrate how mapping can contribute to interpreting sentiments. Design/methodology/approach The authors presented a methodological framework to collect, pre-process, analyse and map public Twitter postings related to the shooting. The authors designed and implemented an emoji training heuristic, which automatically prepares the training data set, a feature needed in Big Data research. The authors improved upon the previous framework by advancing the pre-processing techniques, enhancing feature engineering and optimising the classification models. The authors constructed the sentiment model with a logistic regression classifier and selected features. Finally, the authors presented how to visualise citizen sentiments on maps dynamically using Mapbox. Findings The sentiment model constructed with the automatically annotated training sets using an emoji approach and selected features performs well in classifying tweets into five different sentiment classes, with a macro-averaged F-measure of 0.635, a macro-averaged accuracy of 0.689 and the MAEM of 0.530. Compared to those experimental results in related works, the results are satisfactory, indicating the model is effective and the proposed emoji training heuristic is useful and feasible in multi-class TSA. The maps authors created, provide a much easier-to-understand visual representation of the data, and make it more efficient to monitor citizen sentiments and distributions. Originality/value This work appears to be the first to conduct multi-class sentiment classification on Twitter with automatic annotation of training sets using emojis. Little attention has been paid to applying TSA to monitor the public’s attitudes towards terror attacks and country’s gun policies, the authors consider this work to be a pioneering work. Besides, the authors have introduced a new data set of 2016 Orlando Shooting tweets, which will be made available for other researchers to mine the public’s political opinions about gun policies.

The current state of the legislative implementation of criminal law policy

2020 ◽  
pp. 111-118
Author(s):  
Oleksandr Ostrohliad
Keyword(s):  
Law Enforcement ◽  
Criminal Code ◽  
Practical Significance ◽  
New Approach ◽  
Public Discussion ◽  
Current State ◽  
Criminal Offenses ◽  
Legal Technology ◽  
Logical Semantic

Purpose. The aim of the work is to consider the novelties of the legislative work, which provide for the concept and classification of criminal offenses in accordance with the current edition of the Criminal Code of Ukraine and the draft of the new Code developed by the working group and put up for public discussion. Point out the gaps in the current legislation and the need to revise individual rules of the project in this aspect. The methodology. The methodology includes a comprehensive analysis and generalization of the available scientific and theoretical material and the formulation of appropriate conclusions and recommendations. During the research, the following methods of scientific knowledge were used: terminological, logical-semantic, system-structural, logical-normative, comparative-historical. Results In the course of the study, it was determined that despite the fact that the amendments to the Criminal Code of Ukraine came into force in July of this year, their perfection, in terms of legal technology, raises many objections. On the basis of a comparative study, it was determined that the Draft Criminal Code of Ukraine needs further revision taking into account the opinions of experts in the process of public discussion. Originality. In the course of the study, it was established that the classification of criminal offenses proposed in the new edition of the Criminal Code of Ukraine does not stand up to criticism, since other elements of the classification appear in subsequent articles, which are not covered by the existing one. The draft Code, using a qualitatively new approach to this issue, retains the elements of the previous classification and has no practical significance in law enforcement. Practical significance. The results of the study can be used in law-making activities to improve the norms of the current Criminal Code, to classify criminal offenses, as well as to further improve the draft Criminal Code of Ukraine.

Sign in / Sign up

Export Citation Format

Share Document