Points of Interest Recommendations Based on Check-In Motivations
TL;DR: A novel approach to leverage the check-in data captured by location-based social networks (LBSNs) with an aim to improve POI recommendations through personalized explanations, and its applicability is presented by analyzing a dataset extracted from a popular LBSN.
Abstract: During a trip, tourists are mostly dependent on their mobile phone to select their next points of interest (POI). A mobile application that recommends POIs such as tourist attractions or restaurants is based on the user's location data such as check-in history. This article recommends a novel approach to leverage the check-in data captured by location-based social networks (LBSNs) with an aim to improve POI recommendations through personalized explanations. The proposed algorithm generates a user's motivation profile, and its applicability is presented by analyzing a dataset extracted from a popular LBSN. A between-subject experiment (N = 182) is conducted that shows explanations generated using a user's motivation profile increase transparency, which leads to intent to use the LBSN. Perceived usefulness of the LBSN also increases intent to use. The study indicates that when suggesting a POI, recommender system developers include explanations based on user's motivation behavior profile.
Citations
More filters
TL;DR: Experimental and analytical results show that the proposed method outperforms existing methods, while alleviating the cold-start and sparsity problems that commonly hinder POI recommender systems.
46 citations
01 Jan 2022
TL;DR: Wang et al. as mentioned in this paper investigated the impact of the crisis on mobile marketing and how innovation helps companies apply mobile marketing in the crisis through an analysis of mobile marketing content and strategies before and after the COVID-19 pandemic, using three cases from the tourism industry in China.
Abstract: Even though mobile marketing is acknowledged as one of the most personal and effective approaches to marketing, research on mobile marketing during times of crisis is limited. Following the COVID-19 outbreak, mobile marketing blossomed to capture customers’ attention, providing an opportunity to study how mobile marketing may assist companies in overcoming the crisis and uncertainty. The current study attempts to investigate the impact of the crisis on mobile marketing and how innovation helps companies apply mobile marketing in the crisis through an analysis of mobile marketing content and strategies before and after the COVID-19 pandemic, using three cases from the tourism industry in China. According to the findings, mobile marketing is an effective marketing strategy in times of crisis and uncertainty since it offers companies an effective communication channel with customers and brings marketing benefits. Furthermore, innovation enables companies to respond rapidly to crises and supports their post-crisis recovery. Further, customer value co-creation was attainable during lockdowns based on mobile marketing and innovation integration. These findings have practical implications for businesses that strive to recover and grow after the crisis.KeywordsMobile marketingCrisisInnovationCo-creationTourism industry
References
More filters
TL;DR: As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levels.
Abstract: As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levels
9,583 citations
TL;DR: An overview of recommender systems as well as collaborative filtering methods and algorithms is provided, which explains their evolution, provides an original classification for these systems, identifies areas of future implementation and develops certain areas selected for past, present or future importance.
Abstract: Recommender systems have developed in parallel with the web. They were initially based on demographic, content-based and collaborative filtering. Currently, these systems are incorporating social information. In the future, they will use implicit, local and personal information from the Internet of things. This article provides an overview of recommender systems as well as collaborative filtering methods and algorithms; it also explains their evolution, provides an original classification for these systems, identifies areas of future implementation and develops certain areas selected for past, present or future importance.
2,639 citations
TL;DR: This article presents one class of model-based recommendation algorithms that first determines the similarities between the various items and then uses them to identify the set of items to be recommended, and shows that these item-based algorithms are up to two orders of magnitude faster than the traditional user-neighborhood based recommender systems and provide recommendations with comparable or better quality.
Abstract: The explosive growth of the world-wide-web and the emergence of e-commerce has led to the development of recommender systems---a personalized information filtering technology used to identify a set of items that will be of interest to a certain user. User-based collaborative filtering is the most successful technology for building recommender systems to date and is extensively used in many commercial recommender systems. Unfortunately, the computational complexity of these methods grows linearly with the number of customers, which in typical commercial applications can be several millions. To address these scalability concerns model-based recommendation techniques have been developed. These techniques analyze the user--item matrix to discover relations between the different items and use these relations to compute the list of recommendations.In this article, we present one such class of model-based recommendation algorithms that first determines the similarities between the various items and then uses them to identify the set of items to be recommended. The key steps in this class of algorithms are (i) the method used to compute the similarity between the items, and (ii) the method used to combine these similarities in order to compute the similarity between a basket of items and a candidate recommender item. Our experimental evaluation on eight real datasets shows that these item-based algorithms are up to two orders of magnitude faster than the traditional user-neighborhood based recommender systems and provide recommendations with comparable or better quality.
2,265 citations
TL;DR: In this article, the authors investigate two key group-level determinants of virtual community participation, namely group norms and social identity, and consider their motivational antecedents and mediators.
1,801 citations
TL;DR: This article examined audience uses of the Internet from a uses-and-gratifications perspective and found that contextual age, unwillingness to communicate, social presence, and Internet motives predict outcomes of Internet exposure, affinity and satisfaction.
Abstract: We examined audience uses o f the Internet from a uses-and-gratifications perspective. We expected contextual age, unwillingness to communicate, social presence, and Internet motives to predict outcomes of Internet exposure, affinity and satisfaction. The analyses identified five motives for using the Internet and multivariate links among the antecedents and motives. The results suggested distinctions between instrumental and ritualized Internet use, as well as Internet use serving as a functional alternative to face-to-face interaction.
1,654 citations