Data-Driven Serendipity Navigation in Urban Places

@article{Ge2017DataDrivenSN,
  title={Data-Driven Serendipity Navigation in Urban Places},
  author={Xiaoyu Ge and Ameya Daphalapurkar and Manali Shimpi and Darpun Kohli and Konstantinos Pelechrinis and Panos K. Chrysanthis and Demetrios Zeinalipour-Yazti},
  journal={2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)},
  year={2017},
  pages={2501-2504}
}
With the proliferation of mobile computing and the ability to collect detailed data for the urban environment a number of systems that aim at providing Points of Interest (POIs) and tour recommendations have appeared. The overwhelming majority of these systems aims at providing an optimal recommendation, where optimality refers to objectives of minimizing the distance to be covered or maximizing the quality of the POIs recommended. A major problem is that by focusing on the optimization of… 

Figures from this paper

Serendipity-based Points-of-Interest Navigation
TLDR
MPG, a Mobile Personal Guide that recommends a set of diverse yet surprisingly interesting venues that are aligned to user preferences and a setof routes, constructed from the recommended venues, is designed.
EPUI: Experimental Platform for Urban Informatics
TLDR
A prototype system, namely, EPUI (an Experimental Platform of Urban Informatics), which provides a testbed for exploring and evaluating venues and route recommendation solutions that balance between different objectives including the newly discovered ones.
Serendipity in the city: User evaluations of urban recommender systems
TLDR
This work study user evaluations of serendipity in urban recommender systems through a survey among 1,641 citizens and finds that there is a strong relation between the relevance and novelty of recommendations and the corresponding experienced serendipsity.
Serendipity-based Points-of-Interest Navigation
TLDR
In this article, the authors design MPG, a Mobile Persona that provides a diverse set of recommendations for venue and tour recommendation systems and leaves little room for serendipity.
PrefDiv: Efficient Algorithms for Effective Top-k Result Diversification
TLDR
This work forms an extended version of the result diversification problem, considering three objectives—relevance, diversity, and coverage—and presents a novel approach and algorithms that produce better-diversified results.
What Can We Expect from Navigating?: Exploring Navigation, Wearables and Data Through Critical Design Concepts
TLDR
A collection of design concepts generated as part of the initial stages of a research project that combines a critical design mindset and research through design process to explore these types of questions about how information is communicated to us.

References

SHOWING 1-10 OF 12 REFERENCES
Customized tour recommendations in urban areas
TLDR
This paper focuses on the problem of recommending customized tours in urban settings, and introduces two instances of the TourRec problem, study their complexity, and propose efficient algorithmic solutions.
MPG: Not So Random Exploration of a City
TLDR
This paper designs and introduces MPG (which stands for Mobile Personal Guide), a mobile service that provides a set of diverse venue recommendations better aligned with user preferences and achieves a significantly better Relevancy-Diversity trade-off ratio.
Constructing popular routes from uncertain trajectories
TLDR
A Route Inference framework based on Collective Knowledge (abbreviated as RICK) to construct the popular routes from uncertain trajectories, which is both effective and efficient and can benefit trip planning, traffic management, and animal movement studies.
Travel route recommendation using geotags in photo sharing sites
TLDR
A travel route recommendation method that makes use of the photographers' histories as held by Flickr, and incorporates user preference and present location information into the probabilistic behavior model by combining topic models and Markov models.
Preferential Diversity
TLDR
This paper proposes a novel framework called Preferential Diversity (PrefDiv) that aims to support both relevancy and diversity of user query results and describes an implementation of PrefDiv on top of the HYPRE preference model, which allows users to specify both qualitative and quantitative preferences and unifies them using the concept of preference intensities.
A random walk down Main Street
US suburbs have often been characterized by their relatively low walk accessibility compared to more urban environments, and US urban environments have been char- acterized by low walk accessibility
Multiple Radii DisC Diversity: Result Diversification Based on Dissimilarity and Coverage
TLDR
This article introduces a novel definition of diversity called DisC diversity, and extends its definition to the multiple radii case, where each item is associated with a different radius based on its importance, relevance, or other factors.
M-tree: An Efficient Access Method for Similarity Search in Metric Spaces
TLDR
The results demonstrate that the Mtree indeed extends the domain of applicability beyond the traditional vector spaces, performs reasonably well in high-dimensional data spaces, and scales well in case of growing files.
Distributed Representations of Words and Phrases and their Compositionality
TLDR
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Urban navigation beyond shortest route: The case of safe paths
...
...