Value of Expressions behind the Letter Capitalization in Product Reviews

Pak, Irina; Teh, Phoey Lee

doi:10.1145/3185089.3185150

Cited by 5 publications

(3 citation statements)

References 13 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The author [7] shares various factors in influencing the sentiment level expressed in the textual comments. The example includes using the capital letter [8] tends to mark something for attention, emoticons to visualise the facial expression, and its potential to reverse the meaning of a statement [9]. Also, the test result of using exclamation marks pointed out that adding more exclamation marks on the negative comments will result in higher dissatisfaction [10].…”

Section: A Modelsmentioning

confidence: 99%

Customer Intent Prediction using Sentiment Analysis Techniques

Lye

Teh

2021

2021 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applicat

Self Cite

View full text Add to dashboard Cite

Analysing the voice of the customer (VoC) through the customer intent has many applications ranging from personalised marketing to behaviour study. Individuals express their feelings in a language that is frequently accompanied by ambiguity and figure of speech, making it difficult even for humans to understand. Customer feedback is crucial as part of the customer experience (CX) management in customer retention and improves the sales strategy. Modern research has been using machine learning and word embedding technique for sentiment analysis, and it is focused on the predictive model without further context. In this study, the customer feedback comes in the form of Net Promoter Score (NPS) with a text box for written feedback. We analyse the data and demonstrate a hybrid representation that has resulted in the accuracy improvement of the sentiment classification task and predicting customer intent. The datasets were first trained using Word2Vec with the previous dataset and then fit into the Random Forest classifier, tested as the best configuration to prevent overfitting. The hybrid representation is compared against the baseline sentiment polarity tool through few experiments; the results have shown that the hybrid model has improved accuracy for the sentiment classification task. Lastly, we performed customer intent prediction by using the Power BI influencer module. The outcome of the result can be used as a reference for IT management in decision making.

show abstract

Section: A Modelsmentioning

confidence: 99%

Customer Intent Prediction using Sentiment Analysis Techniques

Lye

Teh

2021

2021 11th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applicat

Self Cite

View full text Add to dashboard Cite

show abstract

“…Research in the field of human-computer interaction and natural language processing may lead the way; extant studies find that even text-based communication can communicate emotion through capitalization, emoticons, and repetition. [38][39][40][41] With virtual and augmented reality becoming increasingly sophisticated, the likelihood that children will learn from these technologies is high. 42 Digital media and technology are increasingly used in classrooms and at home; as such, this kind of inquiry is essential as we look to support our species in an increasingly mediated world.…”

Section: Future Directions and Implicationsmentioning

confidence: 99%

Mobile Technologies and Their Relationship to Children's Ability to Read Nonverbal Emotional Cues: A Cross-Temporal Comparison

Uhls

Broome

Levi

et al. 2020

Cyberpsychology, Behavior, and Social Networking

View full text Add to dashboard Cite

Key social learning occurs during early childhood with lasting effects throughout the lifespan. In the past 10 years, ownership of mobile technology grew rapidly, particularly in households with young children; this has dramatically changed the early learning landscape. With the ubiquity of mobile devices, many have questioned their effect on the social and emotional learning of children. To explore one aspect of this question, we conducted a crosstemporal comparison to compare two cohorts of sixth graders, one measured in 2012 and another in 2017. Each group took tests, one with still photographs of faces (diagnostic analysis of nonverbal accuracy 2 or DANVA2) and one with videotaped vignettes (the child and adolescent social perception measure or CASP), designed to measure their ability to accurately identify nonverbal emotional cues. We sought to explore whether changes in the early learning environment of the 2017 cohort, who grew up with mobile phones and tablets, could be related to participants' ability to read nonverbal emotional cues. We found that sixth-grade students in 2017 performed better than sixth-grade students in 2012 on the DANVA2, but not on the CASP. One possible reason participants improved on the test with still photographs is because mediated communication has become more visual and less text based, and sharing photographs of oneself and others is more common. Accordingly participants may be more accurate at interpreting emotional cues in photographs due to a larger exposure to photographs of faces.

show abstract

“…Additionally, the continent-wise comparison was also performed to see if any differentiation in the influences within the countries. By exploring the fine-grained text [13] and the value of emotional expression [14], this study offers a different way of understanding gamer's experiences. Hence, the present qualitative study, with the aid of semantic analytical tools, aims to discover through text, "What are the elements that motivate gamers to pay to play?"…”

mentioning

confidence: 99%

Pay to Play: Understanding Gamer's Motivation through Semantic Analysis

Teh

Pak

2021

The 23rd International Conference on Information Integration and Web Intelligence

Self Cite

View full text Add to dashboard Cite

Understanding what motivates a gamer to pay to play a game could enhance the gaming industry. One of the ways to understand game players experiences is through exploration via their text communication. This study explores text communication posted on the Steam digital distribution platform on paid-play games. A total of 7255 gamer text communicated were collected and analysed. Reviews from the past pinpointed that elements such as social influence, entertaining features, graphic design, music, and soundtrack used in the game could influence the game playing experience. To study those, we use mix-method (qualitative and quantitative) methods to analyse the data. We invite three human coders to categorise statements associating with its elements and aspects. Next, with the aid of Wmatrix, a semantic analysis system, we tabulate and elaborate the emotion words associating with the gameplay elements. The result shows that the positive feeling of love and joy highly encourages the gamer's overall game playing experience. Elements such as the storyline, design of the Avatar and the entertaining features are the primary motivation of the gameplay.

show abstract

Value of Expressions behind the Letter Capitalization in Product Reviews

Cited by 5 publications

References 13 publications

Customer Intent Prediction using Sentiment Analysis Techniques

Customer Intent Prediction using Sentiment Analysis Techniques

Mobile Technologies and Their Relationship to Children's Ability to Read Nonverbal Emotional Cues: A Cross-Temporal Comparison

Pay to Play: Understanding Gamer's Motivation through Semantic Analysis

Contact Info

Product

Resources

About