Search results

Social media analytics uses data mining platforms, tools and analytics techniques to collect, monitor and analyze massive amounts of social media data to extract useful patterns, gain insight into market requirements and enhance business intelligence. The purpose of this paper is to propose a framework for social media competitive intelligence to enhance business value and market intelligence.

The authors conducted a case study to collect and analyze a data set with nearly half million tweets related to two largest retail chains in the world: Walmart and Costco in the past three months during December 1, 2014-February 28, 2015.

The results of the case study revealed the value of analyzing social media mentions and conducting sentiment analysis and comparison on individual product level. In addition to analyzing the social media data-at-rest, the proposed framework and the case study results also indicate that there is a strong need for creating a social media data application that can conduct real-time social media competitive intelligence for social media data-in-motion.

So far there is little research to guide businesses for social media competitive intelligence. This paper proposes a novel framework for social media competitive intelligence to illustrate how organizations can leverage social media analytics to enhance business value through a case study.

This paper aims to identify how house price affects household consumption.

The authors use a micro-level data set that tracks the house price and consumption of a vast number of households over a period of four years. OLS regression is the main econometric method.

The authors document robust evidence that an increase in house prices stimulates household consumption, regardless of whether a household owns or rents. Moreover, the authors find that both acquiring and losing homeownership negatively affects household consumption. Further investigation suggests significant regional heterogeneity in the relationship between house prices and household consumption.

This is one of the first studies examining the relationship between house price and household consumption in China using micro-level data. Given the uniqueness of the Chinese housing market and China’s fast-growing consumption rate, the study contributes new evidence to the long-lasting debate.

The purpose of this paper is to explore the challenges posed by Big Data to current trends in computation, networking and storage technology at various stages of Big Data analysis. The work aims to bridge the gap between theory and practice, and highlight the areas of potential research.

The study employs a systematic and critical review of the relevant literature to explore the challenges posed by Big Data to hardware technology, and assess the worthiness of hardware technology at various stages of Big Data analysis. Online computer-databases were searched to identify the literature relevant to: Big Data requirements and challenges; and evolution and current trends of hardware technology.

The findings reveal that even though current hardware technology has not evolved with the motivation to support Big Data analysis, it significantly supports Big Data analysis at all stages. However, they also point toward some important shortcomings and challenges of current technology trends. These include: lack of intelligent Big Data sources; need for scalable real-time analysis capability; lack of support (in networks) for latency-bound applications; need for necessary augmentation (in network support) for peer-to-peer networks; and rethinking on cost-effective high-performance storage subsystem.

The study suggests that a lot of research is yet to be done in hardware technology, if full potential of Big Data is to be unlocked.

The study suggests that practitioners need to meticulously choose the hardware infrastructure for Big Data considering the limitations of technology.

This research arms industry, enterprises and organizations with the concise and comprehensive technical-knowledge about the capability of current hardware technology trends in solving Big Data problems. It also highlights the areas of potential research and immediate attention which researchers can exploit to explore new ideas and existing practices.

The purpose of this paper is to address the shortcomings of limited research in forecasting the power of social media in India.

This paper uses sentiment analysis and prediction algorithms to analyze the performance of Indian movies based on data obtained from social media sites. The authors used Twitter4j Java API for extracting the tweets through authenticating connection with Twitter web sites and stored the extracted data in MySQL database and used the data for sentiment analysis. To perform sentiment analysis of Twitter data, the Probabilistic Latent Semantic Analysis classification model is used to find the sentiment score in the form of positive, negative and neutral. The data mining algorithm Fuzzy Inference System is used to implement sentiment analysis and predict movie performance that is classified into three categories: hit, flop and average.

In this study the authors found results of movie performance at the box office, which had been based on fuzzy interface system algorithm for prediction. The fuzzy interface system contains two factors, namely, sentiment score and actor rating to get the accurate result. By calculation of opening weekend collection, the authors found that that the predicted values were approximately same as the actual values. For the movie Singham Returns over method of prediction gave a box office collection as 84 crores and the actual collection turned out to be 88 crores.

The current study suffers from the limitation of not having enough computing resources to crawl the data. For predicting box office collection, there is no correct availability of ticket price information, total number of seats per screen and total number of shows per day on all screens. In the future work the authors can add several other inputs like budget of movie, Central Board of Film Certification rating, movie genre, target audience that will improve the accuracy and quality of the prediction.

The authors used different factors for predicting box office movie performance which had not been used in previous literature. This work is valuable for promoting of product and services of the firms.

Artificial intelligence (AI) applications pose a potential threat to users' data security and privacy due to their high data-dependence nature. This paper aims to investigate an understudied issue in the literature, namely, how users perceive the threat of and decide to use a threatening AI application. In particular, it examines the influencing factors and the mechanisms that affect an individual’s behavioral intention to use facial recognition, a threatening AI.

The authors develop a research model with trust as the key mediating variable by integrating technology threat avoidance theory, the theory of planned behavior and contextual factors related to facial recognition. Then, it is tested through a sequential mixed-methods investigation, including a qualitative study (for model development) of online comments from various platforms and a quantitative study (for model validation) using field survey data.

Perceived threat (triggered by perceived susceptibility and severity) and perceived avoidability (promoted by perceived effectiveness, perceived cost and self-efficacy) have negative and positive relationships, respectively, with an individual’s attitude toward facial recognition applications; these relationships are partially mediated by trust. In addition, perceived avoidability is positively related to perceived behavioral control, which along with attitude and subjective norm is positively related to individuals' intentions to use facial recognition applications.

This paper is among the first to examine the factors that affect the acceptance of threatening AI applications and how. The research findings extend the current literature by providing rich and novel insights into the important roles of perceived threat, perceived avoidability, and trust in affecting an individual’s attitude and intention regarding using threatening AI applications.

This paper aims to propose a novel statistic energy analysis method with fuzzy parameters to study the dynamic and acoustic responses of coupled system with fuzzy parameters, which can expand the applied range of statistic energy analysis method in engineering to some extent.

On the basis of the property of membership level, the uncertain fuzzy parameters are expressed as the interval forms. Interval mathematics and interval expansion principle are adopted to solve the problem with interval parameters. At last, two numerical examples, which include a two-plate coupled system and a single-partition sound-insulation system, are carried out to demonstrate the feasibility and validity of the presented method.

Interval mathematics and interval expansion principle are adopted to solve the problem with interval parameters.

By integrating the interval analysis, optimization technique and Taylor expansion method, two non-probabilistic, set-theoretical statistical energy analyses are proposed for predicting the dynamical and acoustical response of the complex coupled system with uncertain parameters in high-frequency domain.

Nurses' work engagement is critical for the service quality of the hospital. Thus, investigation on the influencing factors of nurses' work engagement has become an important issue. This study addresses this issue by exploring the effect of daily family-to-work conflict (FWC) on next-day work engagement among Chinese nurses.

The theoretical model was tested using 555 experience sampling data from 61 nurses collected for 10 workdays in China.

Nurses' daily FWC is associated with their next-day ego depletion. Moreover, increased ego depletion ultimately reduces their next-day work engagement. In addition, a between-individual factor of frequency of perceived patient gratitude mitigates the effect of FWC on ego depletion and the indirect effect on work engagement via ego depletion.

This study is important to the management of health-care organizations as it carries significant implications for theory and practice toward understanding the influence of FWC among nurses. On the one hand, the authors apply the job demands-resources (JD-R) model as the overarching theoretical framework, which contributes to the authors’ understanding of how FWC impairs work engagement. On the other hand, the authors extend extant theoretical models of FWC by identifying the frequency of perceived patient gratitude as an important contextual factor that counteracts the negative effects of FWC among nurses. Moreover, organizations could encourage patients to express their gratitude to nurses by providing more channels, such as thank-you notes, to offer nurses some support for overcoming the destructive effect of FWC.

This paper is to present an experiment to verify that the motion errors of robust topology optimization results of compliant mechanisms are insensitive to load dispersion.

First, the test pieces of deterministic optimization and robust optimization results are manufactured by the combination of three-dimensional (3D) printing and casting techniques. To measure the displacement of the test piece of compliant mechanism, a displacement measurement method based on the image recognition technique is proposed in this paper.

According to the experimental data analysis, the robust topology optimization results of compliant mechanisms are less sensitive to uncertainties, comparing with the deterministic optimization results.

An experiment is presented to verify the effectiveness of robust topology optimization for compliant mechanisms. The test pieces of deterministic optimization and robust optimization results are manufactured by the combination of 3D printing and casting techniques. By comparing the experimental data, it is found that the motion errors of robust topology optimization results of compliant mechanisms are insensitive to load dispersion.

This study assesses outsourcing risks using the fuzzy analytical hierarchy process (FAHP).

This descriptive research combines both qualitative and quantitative approaches. Risks identified in the literature review were classified with FAHP using questionnaire data from respondents in operations, procurement and risk management in Brazilian Navy Industrial Military Organizations (OMPS-I, by its Portuguese acronym).

The results indicate that FAHP is a method capable of producing relevant information to decision-making in the risk management process. A framework was created incorporating 16 major risks related to outsourcing. The results point to higher inherent risk levels related to outsourcing in the context of OMPS-Is: in order, hidden costs and unrealized savings; loss of knowledge/skills and/or corporate memory and difficulty in reacquiring a function; and loss of opportunities and reputation. The category of economic risk was revealed as the most important.

This study improves understanding of outsourcing risks and improves risk assessment by refining decision-making information and developing a system of decision analysis with several criteria. It also contributes to the development and implementation of a usable version of decision analysis with several criteria at a managerial level.

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.

An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).

A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.

Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.

There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.