Search results

The purpose of this study is to assign polarity score to each post from Facebook fan pages, and then examine whether the Comments submitted by users on a post from fan page have a significant relationship with the popularity of that post. Being aware of how to enhance the popularity of posts will help companies in terms of administrating their fan pages.

In the context of fan page and post popularity, the authors test significance of the relationship between Comments’ polarity and number of Likes and Comments of a post in different Facebook pages by regression method. The data are collected from different fan page posts in Facebook, and a sentiment analysis approach is proposed to accomplish this research.

Results show that the relation between users’ Comments and popularity of fan page posts is strongly significant. Outcomes of this research are useful for every company in terms of monitoring and managing their brand fan pages on social networking sites such as Facebook.

Investigation of factors influencing popularity of fan page posts in social media is almost a new area of study that dates back to recent years. The authors use a sentiment analysis approach to evaluate a new concept describing the relationship between users’ Comments and popularity of posts from Facebook fan pages. Moreover, a part of dataset is extracted from Facebook by a crawler which is an advantage to prior studies.

The purpose of this paper is to evaluate the nature of emotion, self-esteem and life satisfaction tendencies amongst Iranian Muslim consumers when making impulse purchases.

Questionnaires were distributed amongst female Muslim participants at a shopping centre in Yazd, Iran – each of which were selected using cluster and random sampling methods. Data were analysed using descriptive statistics and structural equation modelling techniques, where LISREL software was used to measure the direct and indirect relationships between variables.

Within the sample, there was a direct causal relationship between impulse buying tendencies, impulse buying behaviour and purchasing. Second, there was a negative relationship between self-esteem and life-satisfaction within impulse buying tendencies. Finally, a positive relationship exists between emotion and impulse buying tendencies, which elicits impulse buying behaviour culminating in purchases. Emotion drives these consumers towards dissonance-reducing behaviour, which mediates low self-esteem and life satisfaction – through consumerism as a form of retail therapy. Some of the items purchased on impulse, that fulfilled this role, were hijabs (headscarves) and mantos (a type of tunic/shirt-dress/coat common in Iran).

The hijab is worn by Muslim females across the globe. However, the manto is an item of clothing worn almost exclusively by Iranian females. Therefore, it is likely that Muslim females in different geographies may exhibit similar behavioural traits, but their consumption patterns would substitute this item with a different one, such as an abaya or jilbab, for example.

Whilst the notion of retail therapy is widely understood, the novel contribution of this study lies in highlighting that the purchase of clothing such as hijabs and mantos by Iranian Muslim females is not just driven by rational and emotional decision-making seeking to fulfil religious obligations. There are cases where these religious artefacts are used to raise feelings of self-esteem and life satisfaction within the same individuals.

With the growth of organizations and businesses, customer acquisition and retention processes have become more complex in the long run. That is why customer lifetime value (CLV) has become crucial to sales managers. Predicting the CLV is a strategic weapon and competitive advantage in increasing profitability and identifying customers with more splendid profitability and is one of the essential key performance indicators (KPI) used in customer segmentation. Thus, this paper proposes a stacked ensemble learning method, a combination of multiple machine learning methods, for CLV prediction.

In order to utilize customers’ behavioral features for predicting the value of each customer’s CLV, the data of a textile sales company was used as a case study. The proposed stacked ensemble learning method is compared with several popular predictive methods named deep neural networks, bagging support vector regression, light gradient boosting machine, random forest and extreme gradient boosting.

Empirical results indicate that the regression performance of the stacked ensemble learning method outperformed other methods in terms of normalized rooted mean squared error, normalized mean absolute error and coefficient of determination, at 0.248, 0.364 and 0.848, respectively. In addition, the prediction capability of the proposed method improved significantly after optimizing its hyperparameters.

This paper proposes a stacked ensemble learning method as a new method for accurate CLV prediction. The results and comparisons support the robustness and efficiency of the proposed method for CLV prediction.