Sentiment Classification of Movie Reviews Using Multiple Perspectives

Thet, Tun Thura; Na, Jin‐Cheon; Khoo, Christopher S. G.

doi:10.1007/978-3-540-89533-6_19

Cited by 15 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar techniques were reported by Wijaya and Bressan (2008). Thet, Na, and Khoo (2008b) matched customers’ reviews into relevant sections according to different genres of movies. Similarly, computational linguistics were used by Thet, Na, and Khoo (2008a) to segment movie reviews’ online comments.…”

Section: Literature Reviewmentioning

confidence: 99%

Clustering halal food consumers: A Twitter sentiment analysis

Mostafa

2018

International Journal of Market Research

View full text Add to dashboard Cite

The exponential growth of user-generated social media content raises the possibility of using opinion mining techniques in tracking and monitoring consumers’ preferences. Although the web represents a valuable data mining source about consumers’ opinions, no previous studies have investigated halal food sentiments expressed on social media. In this study, we fill this research gap by analyzing a random sample of 3,919 halal food tweets. A 6,800 seed adjectives expert-predefined lexicon was used to conduct the analysis. A generally positive sentiment toward halal food was detected through descriptive statistical analysis, whereas partitioning around medoids (PAM) clustering indicated that it is possible to cluster halal food consumers into four distinct segments. Thus, it seems that halal food consumers represent a highly heterogeneous group, divisible by level of religiosity, self-identity, animal welfare attitudes, and concern for food authenticity.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Clustering halal food consumers: A Twitter sentiment analysis

Mostafa

2018

International Journal of Market Research

View full text Add to dashboard Cite

show abstract

“…For this study, to analyse the sentiment of consumer-generated content, machine learning algorithms were used. This follows researchers such as Malouf and Mullen (2008) and Thet et al (2008). The sample of posts were analysed for polarity and mentions were assigned sentiment scores of positive, negative or neutral (Dhaoui et al , 2017; Agarwal et al , 2011).…”

Section: Methodsmentioning

confidence: 99%

The effect of nWOM firestorms on South African retail banking

Lappeman

Clark

Evans

et al. 2021

IJBM

View full text Add to dashboard Cite

PurposeThis study analysed the effect of online negative word-of-mouth (nWOM) firestorms in the retail banking sector. By understanding negative sentiment and sentiment recovery across an entire retail banking sector, the research exposed a unique view of banking in South Africa.Design/methodology/approachThe study made use of both a sentiment and topic analysis of over 1.7 million social media posts in South Africa. The methodology made use of both NLP and human validation techniques to measure changes in social media sentiment during online firestorms. This measurement included each of South Africa's major retail banks over a twelve month period.FindingsFrom the analysis, key trigger characteristics for these firestorms (product failures, service failures, social failures and communication failures) were categorised. In addition, the average duration of a firestorm was calculated and factors that impact sentiment recovery were explored.Originality/valueThe study was located in South Africa and, unlike firm level studies, researched nWOM for the whole retail banking sector. A theoretical footprint depicting the typical anatomy of a firestorm was derived in order to aid stakeholders to be more vigilant and better equipped to provide correct intervention in such times of crisis.

show abstract

“…However, their approach used linguistic resources such as clausal extraction tools, POS tagger, and dependency parsing. Thet et al (2008) conducted experiments on aspect-level sentiment classification of movie reviews. They used information extraction techniques such as entity extraction, co-referencing, and pronoun resolution to segment the text into sections, where a particular section focuses on a particular aspect of a product (movie).…”

Section: Related Workmentioning

confidence: 99%

Sentiment classification: a lexical similarity based approach for extracting subjectivity in documents

2011

View full text Add to dashboard Cite

With the growth of social media, document sentiment classification has become an active area of research in this decade. It can be viewed as a special case of topical classification applied only to subjective portions of a document (sources of sentiment). Hence, the key task in document sentiment classification is extracting subjectivity. Existing approaches to extract subjectivity rely heavily on linguistic resources such as sentiment lexicons and complex supervised patterns based on part-of-speech (POS) information. This makes the task of subjective feature extraction complex and resource dependent. In this work, we try to minimize the dependency on linguistic resources in sentiment classification. We propose a simple and statistical methodology called review summary (RSUMM) and use it in combination with well-known feature selection methods to extract subjectivity. Our experimental results on a movie review dataset prove the effectiveness of the proposed methodology.

show abstract

Sentiment Classification of Movie Reviews Using Multiple Perspectives

Cited by 15 publications

References 10 publications

Clustering halal food consumers: A Twitter sentiment analysis

Clustering halal food consumers: A Twitter sentiment analysis

The effect of nWOM firestorms on South African retail banking

Sentiment classification: a lexical similarity based approach for extracting subjectivity in documents

Contact Info

Product

Resources

About