Big Data for Prediction

Technical field of big data for prediction lures the attention of different stakeholders. The reasons are related to the potentials of the big data, which allows for learning from past behavior, discovering patterns and values, and optimizing business processes based on new insights from large databases. However, in order to fully utilize the potentials of big data, its stakeholders need to understand the scope and volume of patenting related to big data usage for prediction. Therefore, this chapter aims to perform an analysis of patenting activities related to big data usage for prediction. This is done by (1) exploring the timeline and geographic distribution of patenting activities, (2) exploring the most active assignees of technical content of interest, (3) detecting the type of the protected technical according to the international patent classification system, and (4) performing text-mining analysis to discover the topics emerging most often in patents' abstracts.

Does the Past Affect the Future? An Analysis of Consumers’ Dining Intentions towards Green Restaurants in the UK

Due to the growing notion of environmental protection, many restaurants have started to apply operational practices to diminish their carbon footprint, leading to the emergence of “green” restaurants. Green restaurants are establishments committed to minimizing adverse environmental consequences throughout their operations. Nevertheless, further research is warranted to examine consumer behavior in this field. Taking the consumers’ perspective, this study uses an augmented theory of planned behavior (TPB) and a cross-section of 896 British diners to explain their dining intentions towards green restaurants. The extended model of the TPB was tested to justify the addition of past behavior and the impact of sociodemographic characteristics. Using structural equation analysis, the results identified past behavior, perceived behavioral control, subjective descriptive norms, and attitude as critical factors influencing behavioral intention. Furthermore, apart from gender, the relationships between sociodemographics and intentions to dine at green restaurants were insignificant. This research provides insightful implications in the green restaurant domain and suggestions for future research.

The Role of Felt Responsibility in Climate Change Political Participation

This research letter investigates the role of feelings of responsibility to reduce climate change (i.e., “felt responsibility”) as an antecedent to climate change related political behaviors and intentions, including willingness to join a campaign, likelihood of supporting pro-climate presidential candidates, and past contact with elected officials. Using nationally representative survey data (n = 1,029) we find that felt responsibility has a significant positive relationship with future behavioral intent, but not past behavior. Implications and future research are discussed.

SessNet: A Hybrid Session-Based Recommender System

<div>Session-based recommendation is the task of predicting user actions during short online sessions. Previous work considers the user to be anonymous in this setting, with no past behavior history available. In reality, this is often not the case, and none of the existing approaches are flexible enough to seamlessly integrate user history when available. In this thesis, we propose a novel hybrid session-based recommender system to perform next-click prediction, which is able to take advantage of historical user preferences when accessible. Specifically, we propose SessNet, a deep profiling session-based recommender system, with a two-stage dichotomy. First, we use bidirectional transformers to model local and global session intent. Second, we concatenate any user information with the current session representation to feed to a feed-forward neural network to identify the next click. Historical user preferences are computed using the sequence-aware embeddings obtained from the first step, allowing us to better understand the users. We evaluate the efficacy of the proposed method using two benchmark datasets, YooChoose1/64 and Dignetica. Our experimental results show that SessNet outperforms state-of-the-art session-based recommenders on P@20 for both datasets.</div>

SessNet: A Hybrid Session-Based Recommender System

<div>Session-based recommendation is the task of predicting user actions during short online sessions. Previous work considers the user to be anonymous in this setting, with no past behavior history available. In reality, this is often not the case, and none of the existing approaches are flexible enough to seamlessly integrate user history when available. In this thesis, we propose a novel hybrid session-based recommender system to perform next-click prediction, which is able to take advantage of historical user preferences when accessible. Specifically, we propose SessNet, a deep profiling session-based recommender system, with a two-stage dichotomy. First, we use bidirectional transformers to model local and global session intent. Second, we concatenate any user information with the current session representation to feed to a feed-forward neural network to identify the next click. Historical user preferences are computed using the sequence-aware embeddings obtained from the first step, allowing us to better understand the users. We evaluate the efficacy of the proposed method using two benchmark datasets, YooChoose1/64 and Dignetica. Our experimental results show that SessNet outperforms state-of-the-art session-based recommenders on P@20 for both datasets.</div>

Using an Integrated Social Cognition Model to Explain Green Purchasing Behavior among Adolescents

Strengthening pro-environmental behaviors such as green purchasing behavior is important for environmental sustainability. An integrated social cognition model which incorporates constructs from habit theory, health action process approach (HAPA), and theory of planned behavior (TPB) is adopted to understand Iranian adolescents’ green purchasing behavior. Using a correlational-prospective design, the study recruited Iranian adolescents aged between 14 and 19 years (N = 2374, n = 1362 (57.4%) females, n = 1012 (42.6%) males; Mean (SD) age = 15.56 (1.22)). At baseline (T1), participants self-reported on the following constructs: past behavior; habit strength (from habit theory); action planning and coping planning (from HAPA); and intention, perceived behavioral control, subjective norm, and attitude (from TPB) with respect to green purchasing behavior. Six months later (T2), participants self-reported on their actions in terms of purchasing green goods. Our findings reported direct effects of perceived behavioral control, subjective norms, attitude, and past behavior on intention; intention and perceived behavioral control on green purchase behavior; intention on two types of planning (i.e., action and coping planning); both types of planning on green purchase behavior; and past green purchase behavior and habits on prospectively measured green purchase behavior. These results indicate that adolescent green purchasing behavior is underpinned by constructs representing motivational, volitional, and automatic processes. This knowledge can help inform the development of theory-based behavior change interventions to improve green purchasing in adolescents, a key developmental period where climate change issues are salient and increased independence and demands in making self-guided decisions are needed.

Assessment Methods for Evaluation of Recommender Systems: A Survey

The recommender system (RS) filters out important information from a large pool of dynamically generated information to set some important decisions in terms of some recommendations according to the user’s past behavior, preferences, and interests. A recommender system is the subclass of information filtering systems that can anticipate the needs of the user before the needs are recognized by the user in the near future. But an evaluation of the recommender system is an important factor as it involves the trust of the user in the system. Various incompatible assessment methods are used for the evaluation of recommender systems, but the proper evaluation of a recommender system needs a particular objective set by the recommender system. This paper surveys and organizes the concepts and definitions of various metrics to assess recommender systems. Also, this survey tries to find out the relationship between the assessment methods and their categorization by type.

Development and Initial Validation of the PILCAST Questionnaire: Understanding Parents’ Intentions to Let Their Child Cycle or Walk to School

Children generally do not meet the recommendation of 60 min of daily physical activity (PA); therefore, active school transportation (AST) is an opportunity to increase PA. To promote AST, the involvement of parents seems essential. Using the theory of planned behavior (TPB), the aim was to develop and validate the PILCAST questionnaire to understand parents’ intentions to let their child cycle or walk to school. Cross-sectional sampling was performed, where 1024 responses were collected from parents. Confirmatory factor analysis indicated acceptable fit indices for the factorial structure according to the TPB, comprising 32 items grouped in 11 latent constructs. All constructs showed satisfying reliability. The regression analysis showed that the TPB explained 55.3% of parents’ intentions to let the child cycle to school and 20.6% regarding walking, increasing by a further 18.3% and 16.6%, respectively, when past behavior was added. The most influential factors regarding cycling were facilitating perceived behavioral control, positive attitudes, subjective and descriptive norms, and for walking, subjective and descriptive norms. The PILCAST questionnaire contributes to a better understanding of the psychological antecedents involving parents’ decisions to let their child cycle or walk to school, and may therefore provide guidance when designing, implementing and evaluating interventions aiming to promote AST.

Determinants of consumer intention to purchase food with safety certifications in emerging markets: evidence from Vietnam

PurposeResearch on the determinants of consumer behavior toward food with safety certifications in Vietnam remains little. The primary objective of this study is to identify the factors affecting Vietnamese consumer intention to purchase safely certified vegetables (safe vegetables) based on an extended theory of planned behavior (TPB).Design/methodology/approachUsing a sample of 361 urban consumers in Hanoi city based on a stratified sampling technique, we applied structural equation modeling (SEM) to test the model.FindingsThe results revealed that the extended TPB succeeded to predict 62% of the variance of intention to purchase safe vegetables. Attitude played the most important role in consumer intention. Notably, the attitude of consumers was the most largely influenced by subjective norms (social effects). Also, subjective norms had a direct effect on intention. Furthermore, consumer trust motivated a favorable attitude to increase purchase intention. The effects of past behavior on intention were verified as direct and indirect through subjective norm and trust combined with attitude. Few socio-demographic variables (e.g. age and education) were found to affect intention indirectly through attitude and subjective norm.Research limitations/implicationsFurther research on the relationship between intention and the actual purchase of safe food is needed.Originality/valueThis extends the application of the TPB to predict consumer intention to purchase safely certified food in a developing country like Vietnam by examining both direct and indirect effects of socio-demographic variables, trust and past behavior on intention.

Predicting donors’ behavior in contributing to health compared to non-health sectors: an application of revised theory of planned behavior in Iran

Purpose This study aims to predict the behavior of donors to give to the health sector compared with other sectors in Shiraz city, South Iran, using the revised theory of planned behavior (TPB). Design/methodology/approach This was a descriptive-analytic cross-sectional study. A standard questionnaire, which comprising 32 items, was used to survey 277 donors affiliated with various charitable associations in the city of Shiraz, South of Iran, in 2018. Participants were selected using stratified sampling and simple random sampling techniques. The authors used a revised TPB, a general model to predict and explain behavior across various types of behaviors and predict behavior based on an individual’s attitudes and beliefs. This model was used to examine the influence of eight social-psychological variables (attitude, perceived behavioral control [PBC], subjective norm, descriptive norm, moral norm, past behavior, intention behavior, self-reported) on an individual’s intention to donate to health sector charity. Data was analyzed using SPSS software version 22.0. Findings The score of all constructs of TPB in the health sector was significantly higher than in the non-health sector (P < 0.001), except for the PBC. This indicates that it does not influence the donors’ behavioral intention in selecting of charitable activity domains (e.g. health and non-health). The constructs of the moral norm, descriptive norm and past behavior in the health sector donors; and the constructs of attitude, moral norms and the variables of the annual income, and work experience in the non-health sector donors were identified as significant predictors of donors’ intention behavior. Moreover, attitude, moral norm, descriptive norm, past behavior, male gender and the annual income were the significant predictors of donors’ intention to give to health charity initiatives. Originality/value One of the most important mechanisms to compensate for the shortage of resources of the health system is the use of donors’ participation capacity. However, different donors act differently in selecting charitable activity domains, including the health sector and non-health sector (e.g. school-building donors’ association, house-building donors’ association, city-building donors’ association, library-building donors’ association, etc.). To attract donors’ participation in the health sector, some interventions to change the behavioral intention of donors towards the health sector through constructs of TPB should be taken.