Integrating GPS trajectory and topics from Twitter stream for human mobility estimation

Miyazawa, Satoshi; Song, Xuan; Xia, Tianqi; Shibasaki, Ryosuke; Kaneda, Hodaka

doi:10.1007/s11704-017-6464-3

Cited by 13 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to energy estimation, a system must be capable of producing a population estimate with high spatial and temporal granularity. The most common form of population estimation is from mobility models such as References [24,31,55,56,59,60]. However, these models typically require GPS traces or cellular information from base stations, which are often not accessible by the public due to privacy concerns.…”

Section: Population Estimationmentioning

confidence: 99%

A Data-driven System for City-wide Energy Footprinting and Apportionment

Wei

Jiang

2021

ACM Trans. Sen. Netw.

View full text Add to dashboard Cite

Energy footprinting has the potential to raise awareness of energy consumption and lead to energy-saving behavior. However, current methods are largely restricted to single buildings; these methods require energy and occupancy monitoring sensor deployments, which can be expensive and difficult to deploy at scale. Further, current methods for estimating energy consumption and population at scale cannot provide fine enough temporal or spatial granularity for a reasonable personal energy footprint estimate. In this work, we present a data-driven system for city-wide estimation of personal energy footprints. This system takes advantage of existing sensing infrastructure and data sources in urban cities to provide energy and population estimates at the building level, even in built environments that do not have existing or accessible energy or population data.

show abstract

Section: Population Estimationmentioning

confidence: 99%

A Data-driven System for City-wide Energy Footprinting and Apportionment

Wei

Jiang

2021

ACM Trans. Sen. Netw.

View full text Add to dashboard Cite

show abstract

“…LBSN data potentially have rich information on people's sentiments, observations, and thoughts. Some notable examples are discovering traffic anomalies (Pan et al, 2013), topic association among cities (Liu et al, 2016), and population density estimation by combining GNSS point density and topics from tweets (Miyazawa et al, 2019).…”

Section: Location Based Social Network (Lbsn)mentioning

confidence: 99%

“…The preprocessing is the essential in natural language processing and we follow our previous work (Miyazawa et al, 2019). After the text cleaning to remove noise and irrelevant text, we conduct word segmentation and normalization for part-of-speech (POS) tagging, then finally we remove "stop words" such as Japanese particles, auxiliary verbs, and pronouns.…”

Section: Preprocessing Textmentioning

confidence: 99%

See 1 more Smart Citation

City-Scale Human Mobility Prediction Model by Integrating GNSS Trajectories and SNS Data Using Long Short-Term Memory

Miyazawa

Song

Jiang

et al. 2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Human mobility analysis on large-scale mobility data has contributed to multiple applications such as urban and transportation planning, disaster preparation and response, tourism, and public health. However, when some unusual events happen, every individual behaves differently depending on their personal routine and background information. To improve the accuracy of the crowd behavior prediction model, understanding supplemental spatiotemporal topics, such as when, where and what people observe and are interested in, is important. In this research, we develop a model integrating social network service (SNS) data into the human mobility prediction model as background information of the mobility. We employ multi-modal deep learning models using Long short-term memory (LSTM) architecture to incorporate SNS data to a human mobility prediction model based on Global Navigation Satellite System (GNSS) data. We process anonymized interpolated GNSS trajectories from mobile phones into mobility sequence with discretized grid IDs, and apply several topic modeling methods on geo-tagged data to extract spatiotemporal topic features in each spatiotemporal unit similar to the mobility data. Thereafter, we integrate the two datasets in the multi-modal deep learning prediction models to predict city-scale mobility. The experiment proves that the models with SNS topics performed better than baseline models.

show abstract

“…In [44], the authors explore the relationship between contextual information in geotagged tweets and GPS traces from smartphones in Japan. They use a specific algorithm to extract contextual information from tweets and use the population distribution from GPS traces into regression models in order to estimate large scale human mobility.…”

Section: Twittermentioning

confidence: 99%

Understanding human mobility using Twitter

Khan¹

View full text Add to dashboard Cite

Advances in communication technology have enabled researchers to look deeply into the dynamics of human mobility. Especially, the advent of online social media has given researchers unprecedented access to a large amount of human movements data both in space and time. By analysing this data, a better understanding of the impact of human movement can be achieved in areas such as disaster management, transportation planning, communication networks and epidemic modelling and prediction. Most of the prior studies make use of data which is either coarse-grained, proprietary or limited in size. This thesis, however, leverages a large set of publicly available location data from geo-tagged tweets in an attempt to gain deeper insights into human mobility dynamics. System-wide mobility analysis of Twitter users is conducted at the suburban level in Australian cities. Specifically, movement models such as Gravity and Radiation are employed to test the movement behaviour of users and it is found that the classic Gravity model captures user movements better than the competitor model. This is followed by individual-based mobility analysis of users by using measures such as Entropy and Predictability which signify the theoretical degree of randomness in movements. It is shown that users can be distinguished on the basis of their movement patterns and two distinct groups 'frequent' and 'casual' are identified. The prediction problem is also explored here with results suggesting that users in Brisbane have higher prediction accuracy than corresponding users in Sydney and Melbourne indicating heterogeneity among various cities. The top 10% of Brisbane's most predictable users have 76.6% prediction accuracy compared to 49.2% for Melbourne and 54.8% for Sydney. The prediction information could be useful for such users and they can be apprised of any update about their likely next location.

show abstract

Integrating GPS trajectory and topics from Twitter stream for human mobility estimation

Cited by 13 publications

References 29 publications

A Data-driven System for City-wide Energy Footprinting and Apportionment

A Data-driven System for City-wide Energy Footprinting and Apportionment

City-Scale Human Mobility Prediction Model by Integrating GNSS Trajectories and SNS Data Using Long Short-Term Memory

Understanding human mobility using Twitter

Contact Info

Product

Resources

About