DeepPIM: A deep neural point-of-interest imputation model

Buru Chang, Yonggyu Park, Seongsoon Kim, Jaewoo Kang

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

A point-of-interest (POI) is a specific location in which someone is interested. In social network services such as Instagram, users share their experiences with text and photos, and link POIs to their posts. POIs can be utilized to understand user preferences and behavior. However, not all posts have POI information. In our study, we found more than half of the posts do not have POI information. The current state-of-the-art POI imputation model adds missing POI information. However, it relies on a conventional machine learning method that requires a substantial amount of laborious feature engineering. To address this problem, we propose DeepPIM, a deep neural POI imputation model that does not require feature engineering. DeepPIM automatically generates textual, visual, user, and temporal features from text, photo, user, and posting time information, respectively. For evaluating DeepPIM, we construct a new large-scale POI dataset. We show that DeepPIM significantly outperforms the current state-of-the-art model on the dataset. Our newly created large-scale POI dataset and the source code of DeepPIM are available at http://github.com/qnfnwkd/DeepPIM.

Original languageEnglish
Pages (from-to)61-71
Number of pages11
JournalInformation Sciences
Volume465
DOIs
Publication statusPublished - 2018 Oct 1

Fingerprint

Imputation
Learning systems
Model
Engineering
User Behavior
User Preferences
Social Networks
Machine Learning

Keywords

  • Deep-learning
  • POI imputation
  • Point-of-interest
  • Social network

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

DeepPIM : A deep neural point-of-interest imputation model. / Chang, Buru; Park, Yonggyu; Kim, Seongsoon; Kang, Jaewoo.

In: Information Sciences, Vol. 465, 01.10.2018, p. 61-71.

Research output: Contribution to journalArticle

Chang, Buru ; Park, Yonggyu ; Kim, Seongsoon ; Kang, Jaewoo. / DeepPIM : A deep neural point-of-interest imputation model. In: Information Sciences. 2018 ; Vol. 465. pp. 61-71.
@article{ffc89292f28d4029a2feece424b00ac3,
title = "DeepPIM: A deep neural point-of-interest imputation model",
abstract = "A point-of-interest (POI) is a specific location in which someone is interested. In social network services such as Instagram, users share their experiences with text and photos, and link POIs to their posts. POIs can be utilized to understand user preferences and behavior. However, not all posts have POI information. In our study, we found more than half of the posts do not have POI information. The current state-of-the-art POI imputation model adds missing POI information. However, it relies on a conventional machine learning method that requires a substantial amount of laborious feature engineering. To address this problem, we propose DeepPIM, a deep neural POI imputation model that does not require feature engineering. DeepPIM automatically generates textual, visual, user, and temporal features from text, photo, user, and posting time information, respectively. For evaluating DeepPIM, we construct a new large-scale POI dataset. We show that DeepPIM significantly outperforms the current state-of-the-art model on the dataset. Our newly created large-scale POI dataset and the source code of DeepPIM are available at http://github.com/qnfnwkd/DeepPIM.",
keywords = "Deep-learning, POI imputation, Point-of-interest, Social network",
author = "Buru Chang and Yonggyu Park and Seongsoon Kim and Jaewoo Kang",
year = "2018",
month = "10",
day = "1",
doi = "10.1016/j.ins.2018.06.065",
language = "English",
volume = "465",
pages = "61--71",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - DeepPIM

T2 - A deep neural point-of-interest imputation model

AU - Chang, Buru

AU - Park, Yonggyu

AU - Kim, Seongsoon

AU - Kang, Jaewoo

PY - 2018/10/1

Y1 - 2018/10/1

N2 - A point-of-interest (POI) is a specific location in which someone is interested. In social network services such as Instagram, users share their experiences with text and photos, and link POIs to their posts. POIs can be utilized to understand user preferences and behavior. However, not all posts have POI information. In our study, we found more than half of the posts do not have POI information. The current state-of-the-art POI imputation model adds missing POI information. However, it relies on a conventional machine learning method that requires a substantial amount of laborious feature engineering. To address this problem, we propose DeepPIM, a deep neural POI imputation model that does not require feature engineering. DeepPIM automatically generates textual, visual, user, and temporal features from text, photo, user, and posting time information, respectively. For evaluating DeepPIM, we construct a new large-scale POI dataset. We show that DeepPIM significantly outperforms the current state-of-the-art model on the dataset. Our newly created large-scale POI dataset and the source code of DeepPIM are available at http://github.com/qnfnwkd/DeepPIM.

AB - A point-of-interest (POI) is a specific location in which someone is interested. In social network services such as Instagram, users share their experiences with text and photos, and link POIs to their posts. POIs can be utilized to understand user preferences and behavior. However, not all posts have POI information. In our study, we found more than half of the posts do not have POI information. The current state-of-the-art POI imputation model adds missing POI information. However, it relies on a conventional machine learning method that requires a substantial amount of laborious feature engineering. To address this problem, we propose DeepPIM, a deep neural POI imputation model that does not require feature engineering. DeepPIM automatically generates textual, visual, user, and temporal features from text, photo, user, and posting time information, respectively. For evaluating DeepPIM, we construct a new large-scale POI dataset. We show that DeepPIM significantly outperforms the current state-of-the-art model on the dataset. Our newly created large-scale POI dataset and the source code of DeepPIM are available at http://github.com/qnfnwkd/DeepPIM.

KW - Deep-learning

KW - POI imputation

KW - Point-of-interest

KW - Social network

UR - http://www.scopus.com/inward/record.url?scp=85049490069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049490069&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2018.06.065

DO - 10.1016/j.ins.2018.06.065

M3 - Article

AN - SCOPUS:85049490069

VL - 465

SP - 61

EP - 71

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -