Main Concepts, State of the Art and Future Research Questions in Sentiment Analysis

Appel, Orestes; Chiclana, Francisco; Carter, Jennifer

doi:10.12700/aph.12.3.2015.3.6

Cited by 14 publications

(9 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, in order to classify emotions as positive or negative in text documents, a sentiment analysis, which is a field of NLP, was conducted to establish an index for the perceptions of public libraries. This study mainly used supervised machine-learning methods, such as Naïve Bayes, decision trees and SVM [32][33][34][35][36], along with proposed unsupervised lexicon-based methods [37,38]. Recently, sentiment analysis using deep learning consisting of long short-term memory (LSTM), which is a type of convolutional neural network (CNN) or recurrent neural network (RNN), has been increasingly used [39][40][41][42][43][44][45].…”

Section: Public Library Image Based On Sentiment Analysismentioning

confidence: 99%

An Analysis of Spatial Accessibility Changes According to the Attractiveness Index of Public Libraries Using Social Media Data

Kim

Lee

2021

Sustainability

View full text Add to dashboard Cite

Public libraries provide equitable access to information for all citizens, and they play an important role in preserving and promoting culture, formal education and self-education, and enriching leisure time. Accordingly, there has been an increasing amount of research on the use factors and accessibility of public libraries, but research on the accessibility of public libraries in non-Western cities is insufficient compared to the corresponding research on other public facilities. In particular, in high-density cities such as Seoul, the Republic of Korea, it may be desirable in terms of sustainability to focus on the qualitative, rather than the quantitative, expansion of public libraries. In previous studies, the attractive factors on the supply side were analyzed using questionnaire surveys, but in this study, the attractive factors for users were quantified in the form of the library attraction index by means of user-generated contents such as location-based social media, and the accessibility was analyzed based on this. The results showed that many public libraries have high accessibility, with a high library attraction index. Therefore, these findings indicate that the qualitative expansion of public libraries is important for information equality. It is meaningful that this study analyzed the attractive factors on the supply side by analyzing the contents generated by users.

show abstract

Section: Public Library Image Based On Sentiment Analysismentioning

confidence: 99%

An Analysis of Spatial Accessibility Changes According to the Attractiveness Index of Public Libraries Using Social Media Data

Kim

Lee

2021

Sustainability

View full text Add to dashboard Cite

show abstract

“…A state of art on sentiment analysis depicts various levels on with sentiment estimation is carried out, different steps involved in the process, the evolution of these processes and finally set of algorithms that help make any analysis of this kind conclusive (Appel, Chiclana, & Carter, 2015). They depict that such techniques have the scope of further contribution in the domain of unsupervised learning which is evidently pointed out by existing literature.…”

Section: Sentiment Analysismentioning

confidence: 99%

Assessment, Implication, and Analysis of Online Consumer Reviews: A Literature Review

Anand

Srivastava

Rakshit

2017

PAJAIS

View full text Add to dashboard Cite

The onset of e-marketplace, virtual communities and social networking has appreciated the influential capability of online consumer reviews (OCR) and therefore necessitate conglomeration of the body of knowledge. This article attempts to conceptually cluster academic literature in both management and technical domain. The study follows a framework which broadly clusters management research under two heads: OCR Assessment and OCR Implication (business implication). Parallel technical literature has been reviewed to reconcile methodologies adopted in the analysis of text content on the web, majorly reviews. Text mining through automated tools, algorithmic contribution (dominant majorly in technical stream literature) and manual assessment (derived from the stream of content analysis) has been studied in this review article. Literature survey of both the domains is analyzed to propose possible area for further research. Usage of text analysis methods along with statistical and data mining techniques to analyze review text and utilize the knowledge creation for solving managerial issues can possibly constitute further work.

show abstract

“…Dr. Potts notices that the so-called Weak (mild) words such as good and bad behave like their opposites when negated (bad = not good, good = not bad), whilst "Strong (intense) words like superb and terrible have 4. Return 2*Polarity(arg1) if Polarity(arg1) = Polarity(arg2).…”

Section: B Component 2: Semantic Rules (Sr) Negation Handling and Amentioning

confidence: 99%

“…• The concept of graduality for polarity intensity expressed through fuzzy sets • The idea that other alternatives -like a number of Natural Language Processing techniques-, besides Supervised Machine Learning, may be viable as well when extracting sentiment from text • The positive contribution that semantic rules and a solid opinion lexicon can have in identifying subjectivity in SA For a complete review of the evolution of the Sentiment Analysis field, please refer to the work of Appel et al [4].…”

Section: Introductionmentioning

confidence: 99%

A hybrid approach to sentiment analysis

Appel

Chiclana

Carter

et al. 2016

2016 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Abstract-This contribution presents a hybrid approach to Sentiment Analysis (SA) encompassing the use of semantic rules, fuzzy sets, unsupervised machine learning techniques and a sentiment lexicon improved with the support of SentiWordNet. A Hybrid Standard Classification is first carried out, which is further enhanced into a Hybrid Advanced approach incorporating linguistic classification of semantic polarity modelled using fuzzy sets. The mechanism of the new SA methodology is illustrated by applying it to compute the polarity of a given sentence and to a benchmarking publicly available dataset: the Movie Review Dataset.

show abstract

Main Concepts, State of the Art and Future Research Questions in Sentiment Analysis

Cited by 14 publications

References 56 publications

An Analysis of Spatial Accessibility Changes According to the Attractiveness Index of Public Libraries Using Social Media Data

An Analysis of Spatial Accessibility Changes According to the Attractiveness Index of Public Libraries Using Social Media Data

Assessment, Implication, and Analysis of Online Consumer Reviews: A Literature Review

A hybrid approach to sentiment analysis

Contact Info

Product

Resources

About