Joon Yeon Choeh

Predicting the helpfulness of online reviews using multilayer perceptron neural networks

With the great development of e-commerce, users can create and publish a wealth of product information through electronic communities. It is difficult, however, for manufacturers to discover the best reviews and to determine the true underlying quality of a product due to the sheer volume of reviews available for a single product. The goal of this paper is to develop models for predicting the helpfulness of reviews, providing a tool that finds the most helpful reviews of a given product. This study intends to propose HPNN (a helpfulness prediction model using a neural network), which uses a back-propagation multilayer perceptron neural network (BPN) model to predict the level of review helpfulness using the determinants of product data, the review characteristics, and the textual characteristics of reviews. The prediction accuracy of HPNN was better than that of a linear regression analysis in terms of the mean-squared error. HPNN can suggest better determinants which have a greater effect on the degree of helpfulness. The results of this study will identify helpful online reviews and will effectively assist in the design of review sites.

The determinants of helpfulness of online reviews

ABSTRACT More and more people are gravitating to reading online product reviews prior to making purchasing decisions. Because a number of reviews that vary in usefulness are posted every day, much attention is being paid to measuring their helpfulness. The goal of this paper is to investigate the various determinants of the helpfulness of reviews, and it also intends to examine the moderating effect of product type, that is, the experience or search goods in relation to the helpfulness of online reviews. The study results show that reviewer reputation, the disclosure of reviewer identity, and review depth positively affect the helpfulness of an online review. The moderating effects of product type exist for these determinants on helpfulness. That is, the number of reviews for a product and the disclosure of reviewer identity have a greater influence on the helpfulness for experience goods, while reviewer reputation, review extremity, and review depth are more important for helpfulness in relation to search goods. The interaction effects exist for average review rating and average review depth for a product with review helpfulness on product sales. The results of the study will identify helpful online reviews and assist in designing review sites effectively.

A Study on the Generation of OLAP Data Cube Based on 3D Visualization Interaction

This paper proposes a new method of creating 3D visual data cubes for high volume/dimension OLAP data analysis with intuitive region selection. Previous methods construct data cubes directly from a data warehouse and build table format cubes with multi-dimensional attributes, in order to specify target ranges for analysis. However, it is a difficult task to select appropriate attributes and their ranges from high cardinality of dimensions with hierarchical structure. The new method reduces the number of dimensions according to the levels of relationship, then confines analysis target ranges with intuitive 3D graphical interface to build an analysis target cube.

Exploring the determinants of and predicting the helpfulness of online user reviews using decision trees

Purpose The purpose of this paper is to suggest important determinants for helpfulness from the reviews’ product data, review characteristics, and textual characteristics, and identify the more crucial factors among these determinants by using statistical methods. Furthermore, this study intends to propose a classification-based review recommender using a decision tree (CRDT) that uses a decision tree to identify and recommend reviews that have a high level of helpfulness. Design/methodology/approach This study used publicly available data from Amazon.com to construct measures of determinants and helpfulness. To examine this, the authors collected data about economic transactions on Amazon.com and analyzed the associated review system. The final sample included 10,000 reviews composed of 4,799 helpful and 5,201 not helpful reviews. Findings The study selected more crucial determinants from a comprehensive group of product, reviewer, and textual characteristics through using a t-test and logistics regression. The five important variables found to be significant in both t-test and logistic regression analysis were the total number of reviews for the product, the reviewer’s history macro, the reviewer’s rank, the disclosure of the reviewer’s name, and the length of the review in words. The decision tree method produced decision rules for determining helpfulness from the value of the product data, review characteristics, and textual characteristics. The prediction accuracy of CRDT was better than that of the k-nearest neighbor (kNN) method and linear multivariate discriminant analysis in terms of prediction error. CRDT can suggest better determinants that have a greater effect on the degree of helpfulness. Practical implications The important factors suggested as affecting review helpfulness should be considered in the design of websites, as online retail sites with more helpful reviews can provide a greater potential value to customers. The results of the study suggest managers and marketers better understand customers’ review and increase the value to customers by proving enhanced diagnosticity to consumers. Originality/value This study is different from previous studies in that it investigated the holistic aspect of determinants, that is, product, review, and textual characteristics for classifying helpful reviews, and selected more crucial determinants from a comprehensive group of product, reviewer, and textual characteristics by using a t-test and logistics regression. This study utilized a decision tree, which has rarely been used in predicting review helpfulness, to provide rules for identifying helpful online reviews.

Fast and robust copy-move forgery detection based on scale-space representation

Copy-move forgery (CMF), which copies a part of an image and pastes it into another region, is one of the most common methods for digital image tampering. For CMF detection (CMFD), we propose a fast and robust approach that can handle several geometric transformations including rotation, scaling, sheering, and reflection. In the proposed CMFD design, keypoints and their descriptors are extracted from the image based on the Scale Invariant Feature Transform (SIFT). Then, an improved matching operation that can handle multiple copy-move forgeries is performed to detect matched pairs located in duplicated regions. Next, the geometric transformation between duplicated regions is estimated using a subset of reliable matched pairs which are obtained using the SIFT scale space representation. In our simulation, we present comparative results between the proposed algorithm and state-of-the-art ones with proven performance guarantees.

Preprocessing for elderly speech recognition of smart devices

HighlightsPreprocessed elderly voice signals were tested with an android smart phone.Speech recognition accuracy increased to 1.5% by increasing the speech rate.Speech recognition accuracy increased to 4.2% by eliminating intersyllabic pauses.Speech recognition accuracy increased to 6% by boosting formant frequency bands.After all the preprocessing, 12% increase in the recognition accuracy was achieved. Due to the increasing aging population in modern society and to the proliferation of smart devices, there is a need to enhance speech recognition among smart devices in order to make information easily accessible to the elderly as it is to the younger population. In general, speech recognition systems are optimized to an average adults voice and tend to exhibit a lower accuracy rate when recognizing an elderly persons voice, due to the effects of speech articulation and speaking style. Additional costs are bound to be incurred when adding modifications to current speech recognitions systems for better speech recognition among elderly users. Thus, using a preprocessing application on a smart device can not only deliver better speech recognition but also substantially reduce any added costs. Audio samples of 50 words uttered by 80 elderly and young adults were collected and comparatively analyzed. The speech patterns of the elderly have a slower speech rate with longer inter-syllabic silence length and slightly lower speech intelligibility. The speech recognition rate for elderly adults could be improved by means of increasing the speech rate, adding a 1.5% increase in accuracy, eliminating silence periods, adding another 4.2% increase in accuracy, and boosting the energy of the formant frequency bands for a 6% boost in accuracy. After all the preprocessing, a 12% increase in the accuracy of elderly speech recognition was achieved. Through this study, we show that speech recognition of elderly voices can be improved through modifying specific aspects of differences in speech articulation and speaking style. In the future, we will conduct studies on methods that can precisely measure and adjust speech rate and find additional factors that impact intelligibility.

Computer Assisted English Learning System with Gestures for Young Children

Kids use the computer assisted language learning systems to learn English. The contents of the system are well designed and kids enjoy them. From Cognitive Psychology we found gestures played useful role in learning so we developed the language learning system utilizing gestures. The system provides similar contents as the existing system but tries to enforce users to follow gestures related to given words. We compared the proposed system with an existing one in terms of memorizing test scores. The average improvement achieved using the proposed system was little better than one achieved using the existing system.

User-Personality Classification Based on the Non-Verbal Cues from Spoken Conversations

Abstract Technology that detects user personality based on user speech signals must be researched to enhance the function of interaction between a user and virtual agent that takes place through a speech interface. In this study, personality patterns were automatically classified as either extroverted or introverted. Personality patterns were recognized based on non-verbal cues such as the rate, energy, pitch, and silent intervals of speech with patterns of their change. Through experimentation, a maximum pattern classification accuracy of 86.3% was achieved. Using the same data, another pattern classification test was manually carried out by people to see how well the automatic pattern classification of personal traits performed. The results in the second manual test showed an accuracy of 86.6%. This proves that the automatic pattern classification of personal traits can achieve results comparable to the level of performance accomplished by humans. The Silent Intervals feature of the automatic pattern cl...

The interactive impact of online word-of-mouth and review helpfulness on box office revenue

Purpose While a number of studies examined the eWOM (online word-of-mouth) factors affecting box office, the studies on the impact of review helpfulness on box office are lacking. The purpose of this paper is to fill the void in previous studies and further extend prior work regarding eWOM and box office. In order to explain the interaction effect of helpfulness with other variables on product sales, this study posits that review characteristics such as number of reviews, review rating, review length interact with review helpfulness to have an influence on box office. Further, as the studies that have examined whether eWOM factors are significant in box office performances for the international markets other than US are lacking, this study is targeting Korean markets to validate the effect of eWOM on box office. Design/methodology/approach This study used publicly available data from www.naver.com to build a sample of online review data concerning box office. The final sample of the study included 2090 movies. Findings The results indicated that in cases when the review is helpful, the number of reviews and review length are more greatly influencing box office. Review rating, review extremity, and helpfulness for reviewer are important determinants for review helpfulness. Practical implications Managers can concentrate on the review rating and review extremity of online customer reviews in the design of online sites for movies. The design of user review systems can follow the direction that promotes more helpfulness for online user reviews based on an enhanced understanding of what drives helpfulness voting. Originality/value Given that previous studies on the effect of review helpfulness on box office are lacking, it contributes to eWOM literature by investigating the impact of review helpfulness on box office revenue.

Perceptual mapping based on web search queries and consumer forum comments

Consumers’ online activities such as keyword searching and writing reviews can provide valuable information that reflects their perception of the market. This study proposes ways to analyze market structure and draw a perceptual map from the following two types of online data: keyword search and online consumer forum data. We apply our methodology to the imported car brands in South Korea automobile market. The multidimensional scaling (MDS) results provide different consumer insights depending on the nature of data. The inter-brand similarity values derived from the proposed two metrics are shown to be correlated. Especially, using consumer forum data, we apply our metric to analyzing the market structure of two sub-markets: midsize sedan and compact crossover sport utility vehicle (SUV). Furthermore, utilizing the proposed measures, we calculate the prototypicality of a brand and demonstrate its positive effect on sales. Marketing managers can apply our technique to understand the market structure and perform longitudinal studies to monitor consumers’ perceptual changes without conducting a time-consuming, traditional survey method.