A Location and Intention Oriented Recommendation Method for Accuracy Enhancement over Big Data

Developing smart city services using intent‐aware recommendation systems: A survey

“…30 In this regard, IARS strive to model real-time user needs to recommend items. 31 IARS enhance the user experience by capturing real-time user needs, aspirations, interests, and social influence and recommending services in smart cities. 1,2,13 These recommenders have the potential in transportation, agriculture, tourism, home management, industrial control, F I G U R E 1 Recommendation process using intent-aware recommendation systems (IARS)…”

“…The concept of intent is broad; therefore, different definitions are used in the literature, that is, in the social IoT context, the intent is defined as the potential motivation of an individual to perform an activity. 31 The intent is the declaration of a user to do a task, which could be identified using implicit and explicit approaches. Implicit intent is identified by recording user traces from social media, contextual features, query logs, and other indirect methods.…”

“…19 IARS can recommend potential items based on user likelihood, their preferences, and intentions. 31 These systems enhance efficiency by promoting the concept of intelligence in recommender systems. Different intelligent techniques can be employed to develop a robust system that can satisfy user demands and business needs and support supply chain management.…”

“…However, these systems often recommend items that are not relevant to the actual intentions of the user of doing an activity or buying a product; thus, there is a need to consider intent in recommendations. 31 User intentions can be extracted from their interactions with other related information sources like social media, web search, and user context. A vast variety of intelligent information resources offered by IoT, RFIDs, and sensory networks could model user intent.…”

“…Tu et al 177 propose a CF parallel algorithm to respond to the data sparsity, lack of scalability, and lower efficiency challenges in big data, using Apache Spark. An improved technique of normalized processing in ALS-WR (Alternating Intent-aware behavior extraction 168,[192][193][194][195][196] Intent-aware results optimization 31,[197][198][199][200][201][202][203][204] least squares with weighted regularization) is proposed to solve the problem of data filtering on large-scale clusters. 177 ALS-WR algorithm is incorporated into the Apache Spark parallel computing framework to enhance efficiency in terms of computation speed.…”