A Comparison of Sentiment Analysis Techniques: Polarizing Movie Blogs

Annett, Michelle; Kondrak, Grzegorz

doi:10.1007/978-3-540-68825-9_3

Cited by 109 publications

(61 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…positive or negative. Two common approaches in this area are lexical and machine learning, each with its own merits and limitations (Annett and Kondrak 2008;Li and Liu 2012). A dictionary or lexicon of pre-tagged words is applied in lexical approaches.…”

Section: Step 3: Sentiment Analysismentioning

confidence: 99%

Does reliable information matter? Towards a trustworthy co-created recommendation model by mining unboxing reviews

Pham

Chuang

et al. 2015

Inf Syst E-Bus Manage

View full text Add to dashboard Cite

Online review forums provide customers with powerful platforms to express opinions and influence business trends, while allowing firms to collaborate and co-create value with customers. However, information overload due to the huge amount of reviews posted daily complicates the efforts of consumers to locate reliable information when making a purchase decision. Therefore, this study develops a trustworthy co-created recommendation model. The proposed model mines unboxing reviews, calculates the trust scores of the reviewers, and then generates the recommended products by combing this information with customer preferences using a multi-criteria decision-making method. An illustrative example of mobile phones demonstrates the recommendation procedure of the proposed model. The proposed model is evaluated via an empirical experiment to examine the satisfaction of study participants by using a seven-point Likert scale. An analysis of the structural equation modelling results indicates that three factors (i.e. confidence in decision quality, enhanced problem-solving ability, and satisfaction with resource expenditure) significantly and positively affect the purchase decision-making process. Moreover, the proposed model outperforms a baseline model in all four factors, ultimately increasing user satisfaction. In addition to its theoretical framework for co-creating value with customers to develop a trustworthy co-created recommendation model, as supported by various theories of trust, the proposed model provides further insights into the role of customer reviews in designing recommendation models, as well as the extent to which such models impact user decisions.

show abstract

Section: Step 3: Sentiment Analysismentioning

confidence: 99%

Does reliable information matter? Towards a trustworthy co-created recommendation model by mining unboxing reviews

Pham

Chuang

et al. 2015

Inf Syst E-Bus Manage

View full text Add to dashboard Cite

show abstract

“…As a starting point of comprehension, Michelle Annett and Grzegorz Kondrak's study poses as a demonstration of the comparison of different sentiment analysis methods [1]. This was achieved by applying them to an available set of movie reviews.…”

Section: Related Workmentioning

confidence: 99%

“…[1] In 2013, Asia-Pacific emerged as the strongest business to consumer (B2C) e-commerce region in the world with sales of around 567.3 billion USD. E-commerce in India has grown the fastest in this region with sales touching almost 20 billion USD in 2015, with a growth rate of 700% since its inception in 2009 (2.5 billion).…”

Section: Introductionmentioning

confidence: 99%

Twitter Sentiment Analysis on E-commerce Websites in India

Jhaveri¹,

Chaudhari²,

Kurup³

2015

IJCA

View full text Add to dashboard Cite

In today's era, social media has become a valuable source of information, where people express their opinions. Analysis of such opinion-related data can provide productive insights. When these opinions are relevant to a company, accurate analysis can provide them with information like product quality, influencers affecting other customer decisions, early feedback on newly launched products, company news, trends and also knowledge about their competitors. Hence, harnessing and extracting insights from these sentiments is necessary for these companies to implement effective marketing strategies and better customer service. Carrying the same notion forward, we decided to extract sentiments from Twitter relevant to two e-commerce giants in India, Flipkart and Snapdeal. In this paper, various lexicon based approaches are applied and their accuracy is investigated.

show abstract

“…More recently, Pang and Lee (2008) and Liu (2012) have conducted extensive surveys of the open challenges in this research area. Opinion mining techniques have been devised and evaluated on many domains, including news stories (Godbole et al 2007), films (Annett and Kondrak 2008;Zhou and Chaovalit 2008), electronic gadgets (Hu and Liu 2004b;Titov and McDonald 2008), and hotels (Pekar and Ou 2008;Ye et al 2009;O'Connor 2010).…”

Section: Overall Sentiment Estimationmentioning

confidence: 99%

Good location, terrible food: detecting feature sentiment in user-generated reviews

Cataldi

Ballatore

Tiddi

et al. 2013

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

A growing corpus of online informal reviews is generated every day by non-experts, on social networks and blogs, about an unlimited range of products and services. Users do not only express holistic opinions, but often focus on specific features of their interest. The automatic understanding of "what people think" at the feature level can greatly support decision making, both for consumers and producers. In this paper, we present an approach to feature-level sentiment detection that integrates natural language processing with statistical techniques, in order to extract users' opinions about specific features of products and services from usergenerated reviews. First, we extract domain features, and each review is modelled as a lexical dependency graph. Second, for each review, we estimate the polarity relative to the features by leveraging the syntactic dependencies between the terms. The approach is evaluated against a ground truth consisting of set of usergenerated reviews, manually annotated by 39 human subjects and available online, showing its human-like ability to capture feature-level opinions.

show abstract

A Comparison of Sentiment Analysis Techniques: Polarizing Movie Blogs

Cited by 109 publications

References 9 publications

Does reliable information matter? Towards a trustworthy co-created recommendation model by mining unboxing reviews

Does reliable information matter? Towards a trustworthy co-created recommendation model by mining unboxing reviews

Twitter Sentiment Analysis on E-commerce Websites in India

Good location, terrible food: detecting feature sentiment in user-generated reviews

Contact Info

Product

Resources

About