Search results
1 – 10 of 15Richard A Owusu, Crispin M Mutshinda, Imoh Antai, Kofi Q Dadzie and Evelyn M Winston
– The purpose of this paper is to identify user-generated content (UGC) features that determine web purchase decision making.
Abstract
Purpose
The purpose of this paper is to identify user-generated content (UGC) features that determine web purchase decision making.
Design/methodology/approach
The authors embed a spike-and-slab Bayesian variable selection mechanism into a logistic regression model to identify the UGC features that are critical to web purchase intent. This enables us to make a highly reliable analysis of survey data.
Findings
The results indicate that the web purchase decision is driven by the relevance, up-to-dateness and credibility of the UGC information content.
Research limitations/implications
The results show that the characteristics of UGC are seen as positive and the medium enables consumers to sort information and concentrate on aspects of the message that are similar to traditional word-of-mouth (WOM). One important implication is the relative importance of credibility which has been previously hypothesized to be lower in the electronic word-of-mouth (e-WOM) context. The results show that consumers consider credibility important as the improved technology provides more possibilities to find out about that factor. A limitation is that the data are not fully representative of the general population but our Bayesian method gives us high analytical quality.
Practical implications
The study shows that UGC impacts consumer online purchase intentions. Marketers should understand the wide range of media that provide UGC and they should concentrate on the relevance, up-to-dateness and credibility of product information that they provide.
Originality/value
The analytical quality of the spike- and- slab Bayesian method suggests a new way of understanding the impact of aspects of UGC on consumers.
Details
Keywords
Zhe Yu, Raquel Prado, Steve C. Cramer, Erin B. Quinlan and Hernando Ombao
We develop a Bayesian approach for modeling brain activation and connectivity from functional magnetic resonance image (fMRI) data. Our approach simultaneously estimates local…
Abstract
We develop a Bayesian approach for modeling brain activation and connectivity from functional magnetic resonance image (fMRI) data. Our approach simultaneously estimates local hemodynamic response functions (HRFs) and activation parameters, as well as global effective and functional connectivity parameters. Existing methods assume identical HRFs across brain regions, which may lead to erroneous conclusions in inferring activation and connectivity patterns. Our approach addresses this limitation by estimating region-specific HRFs. Additionally, it enables neuroscientists to compare effective connectivity networks for different experimental conditions. Furthermore, the use of spike and slab priors on the connectivity parameters allows us to directly select significant effective connectivities in a given network.
We include a simulation study that demonstrates that, compared to the standard generalized linear model (GLM) approach, our model generally has higher power and lower type I error and bias than the GLM approach, and it also has the ability to capture condition-specific connectivities. We applied our approach to a dataset from a stroke study and found different effective connectivity patterns for task and rest conditions in certain brain regions of interest (ROIs).
Details
Keywords
Many recent chapters have investigated whether data from internet search engines such as Google can help improve nowcasts or short-term forecasts of macroeconomic variables. These…
Abstract
Many recent chapters have investigated whether data from internet search engines such as Google can help improve nowcasts or short-term forecasts of macroeconomic variables. These chapters construct variables based on Google searches and use them as explanatory variables in regression models. We add to this literature by nowcasting using dynamic model selection (DMS) methods which allow for model switching between time-varying parameter regression models. This is potentially useful in an environment of coefficient instability and over-parameterization which can arise when forecasting with Google variables. We extend the DMS methodology by allowing for the model switching to be controlled by the Google variables through what we call “Google probabilities”: instead of using Google variables as regressors, we allow them to determine which nowcasting model should be used at each point in time. In an empirical exercise involving nine major monthly US macroeconomic variables, we find DMS methods to provide large improvements in nowcasting. Our use of Google model probabilities within DMS often performs better than conventional DMS methods.
Details
Keywords
Jerry H. Ratcliffe, Amber Perenzin and Evan T. Sorg
The purpose of this paper is to evaluate the violence-reduction effects following an FBI-led gang takedown in South Central Los Angeles.
Abstract
Purpose
The purpose of this paper is to evaluate the violence-reduction effects following an FBI-led gang takedown in South Central Los Angeles.
Design/methodology/approach
The time series impact of the intervention was estimated using a Bayesian diffusion-regression state-space model designed to infer a causal effect of an intervention using data from a similar (non-targeted) gang area as a control.
Findings
A statistically significant 22 percent reduction in violent crime was observed, a reduction that lasted at least nine months after the interdiction.
Research limitations/implications
The research method does make assumptions about the equivalency of the control area, though statistical checks are employed to confirm the control area crime rate trended similarly to the target area prior to the intervention.
Practical implications
The paper demonstrates a minimum nine-month benefit to a gang takedown in the target area, suggesting that relatively long-term benefits from focused law enforcement activity are possible.
Social implications
Longer-term crime reduction beyond just the day of the intervention can aid communities struggling with high crime and rampant gang activity.
Originality/value
Few FBI-led gang task force interventions have been studied for their crime reduction benefit at the neighborhood level. This study adds to that limited literature. It also introduces a methodology that can incorporate crime rates from a control area into the analysis, and overcome some limitations imposed by ARIMA modeling.
Details
Keywords
Anette Rantanen, Joni Salminen, Filip Ginter and Bernard J. Jansen
User-generated social media comments can be a useful source of information for understanding online corporate reputation. However, the manual classification of these comments is…
Abstract
Purpose
User-generated social media comments can be a useful source of information for understanding online corporate reputation. However, the manual classification of these comments is challenging due to their high volume and unstructured nature. The purpose of this paper is to develop a classification framework and machine learning model to overcome these limitations.
Design/methodology/approach
The authors create a multi-dimensional classification framework for the online corporate reputation that includes six main dimensions synthesized from prior literature: quality, reliability, responsibility, successfulness, pleasantness and innovativeness. To evaluate the classification framework’s performance on real data, the authors retrieve 19,991 social media comments about two Finnish banks and use a convolutional neural network (CNN) to classify automatically the comments based on manually annotated training data.
Findings
After parameter optimization, the neural network achieves an accuracy between 52.7 and 65.2 percent on real-world data, which is reasonable given the high number of classes. The findings also indicate that prior work has not captured all the facets of online corporate reputation.
Practical implications
For practical purposes, the authors provide a comprehensive classification framework for online corporate reputation, which companies and organizations operating in various domains can use. Moreover, the authors demonstrate that using a limited amount of training data can yield a satisfactory multiclass classifier when using CNN.
Originality/value
This is the first attempt at automatically classifying online corporate reputation using an online-specific classification framework.
Details
Keywords
The purpose of this paper is to draw on the elaboration likelihood model to examine location-based services (LBS) users’ privacy concern.
Abstract
Purpose
The purpose of this paper is to draw on the elaboration likelihood model to examine location-based services (LBS) users’ privacy concern.
Design/methodology/approach
Based on the 266 valid responses collected from a survey, structural equation modeling was employed to examine the research model.
Findings
The results indicated that privacy concern receives a dual influence from both central cues and peripheral cues. Central cues include privacy policy and information quality, whereas peripheral cues include reputation and privacy seals. Privacy control moderates the effects of privacy policy and privacy seals on privacy concern.
Research limitations/implications
The results imply that service providers need to consider both central and peripheral cues in order to mitigate users’ privacy concern associated with using LBS.
Originality/value
Although previous research has found the effect of privacy concern on user adoption of LBS, it has seldom examined the influence processes of external factors on privacy concern. This research tries to fill the gap.
Details
Keywords
Trishala Chauhan, Shilpa Sindhu and Rahul S. Mor
In this global digital era, health-care companies are increasing their presence on the internet through branded content that serves as a connecting link between customers and…
Abstract
Purpose
In this global digital era, health-care companies are increasing their presence on the internet through branded content that serves as a connecting link between customers and brands. However, there is a limited understanding of branded content’s impact on customers. Thus, this paper aims to empirically analyse customer engagement for branded content in the health-care sector.
Design/methodology/approach
The factors impacting customer engagement for branded content were identified and analysed using the Decision-Making Trial and Evaluation Laboratory approach to get their significance and the cause and effect relationship.
Findings
It emerged that co-creation is the most significant factor, having a substantial relationship with all other factors. It is substantiated that health-care companies can increase the intensity of customer engagement by delivering more authentic and relevant content and having an appealing look in a time-bound manner. This will increase the usefulness and entertaining value of the content.
Originality/value
The research findings contribute to the customer engagement dimension in the health-care sector and help the companies construct effective branded content leading towards higher customer engagement.
Details