Identifying Human Daily Activity Types with Time-Aware Interactions
Human activities embedded in crowdsourced data, such as social media trajectory, represent individual daily styles and patterns, which are valuable in many applications. However, the accurate identification of human activity types (HATs) from social media is challenging, possibly because interaction...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/24/8922 |
| _version_ | 1797544766790959104 |
|---|---|
| author | Renyao Chen Hong Yao Runjia Li Xiaojun Kang Shengwen Li Lijun Dong Junfang Gong |
| author_facet | Renyao Chen Hong Yao Runjia Li Xiaojun Kang Shengwen Li Lijun Dong Junfang Gong |
| author_sort | Renyao Chen |
| collection | DOAJ |
| description | Human activities embedded in crowdsourced data, such as social media trajectory, represent individual daily styles and patterns, which are valuable in many applications. However, the accurate identification of human activity types (HATs) from social media is challenging, possibly because interactions between posts and users at different time are overlooked. To fill this gap, we propose a novel model that introduces the interactions hidden in social media and synthesizes Graph Convolutional Network (GCN) for identifying HAT. The model first characterizes interactions among words, posts, dates, and users, and then derives a Time Gated Human Activity Graph Convolutional Network (TG-HAGCN) to predict the HATs of social media trajectory. To examine the proposed model performance, we built a new dataset including interactions between post content, post time, and users from the open Yelp dataset. Experimental results show that exploiting interactions hidden in social media to recognize HATs achieves state-of-the-art performance with high accuracy. The study indicates that interactions among social media promotes ability of machine learning on social media data mining and intelligent applications, and offers a reference solution for how to fuse multi-type heterogeneous data in social media. |
| first_indexed | 2024-03-10T14:05:06Z |
| format | Article |
| id | doaj.art-9916d423da6b41c6a6e984bd000c8310 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T14:05:06Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-9916d423da6b41c6a6e984bd000c83102023-11-21T00:45:37ZengMDPI AGApplied Sciences2076-34172020-12-011024892210.3390/app10248922Identifying Human Daily Activity Types with Time-Aware InteractionsRenyao Chen0Hong Yao1Runjia Li2Xiaojun Kang3Shengwen Li4Lijun Dong5Junfang Gong6School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430074, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430074, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaSchool of Computer Science, China University of Geosciences, Wuhan 430074, ChinaSchool of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaHuman activities embedded in crowdsourced data, such as social media trajectory, represent individual daily styles and patterns, which are valuable in many applications. However, the accurate identification of human activity types (HATs) from social media is challenging, possibly because interactions between posts and users at different time are overlooked. To fill this gap, we propose a novel model that introduces the interactions hidden in social media and synthesizes Graph Convolutional Network (GCN) for identifying HAT. The model first characterizes interactions among words, posts, dates, and users, and then derives a Time Gated Human Activity Graph Convolutional Network (TG-HAGCN) to predict the HATs of social media trajectory. To examine the proposed model performance, we built a new dataset including interactions between post content, post time, and users from the open Yelp dataset. Experimental results show that exploiting interactions hidden in social media to recognize HATs achieves state-of-the-art performance with high accuracy. The study indicates that interactions among social media promotes ability of machine learning on social media data mining and intelligent applications, and offers a reference solution for how to fuse multi-type heterogeneous data in social media.https://www.mdpi.com/2076-3417/10/24/8922human activity recognitionsocial mediaGraph Convolutional Network |
| spellingShingle | Renyao Chen Hong Yao Runjia Li Xiaojun Kang Shengwen Li Lijun Dong Junfang Gong Identifying Human Daily Activity Types with Time-Aware Interactions Applied Sciences human activity recognition social media Graph Convolutional Network |
| title | Identifying Human Daily Activity Types with Time-Aware Interactions |
| title_full | Identifying Human Daily Activity Types with Time-Aware Interactions |
| title_fullStr | Identifying Human Daily Activity Types with Time-Aware Interactions |
| title_full_unstemmed | Identifying Human Daily Activity Types with Time-Aware Interactions |
| title_short | Identifying Human Daily Activity Types with Time-Aware Interactions |
| title_sort | identifying human daily activity types with time aware interactions |
| topic | human activity recognition social media Graph Convolutional Network |
| url | https://www.mdpi.com/2076-3417/10/24/8922 |
| work_keys_str_mv | AT renyaochen identifyinghumandailyactivitytypeswithtimeawareinteractions AT hongyao identifyinghumandailyactivitytypeswithtimeawareinteractions AT runjiali identifyinghumandailyactivitytypeswithtimeawareinteractions AT xiaojunkang identifyinghumandailyactivitytypeswithtimeawareinteractions AT shengwenli identifyinghumandailyactivitytypeswithtimeawareinteractions AT lijundong identifyinghumandailyactivitytypeswithtimeawareinteractions AT junfanggong identifyinghumandailyactivitytypeswithtimeawareinteractions |