Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
A survey on mobile social signal processing
Palaghias N., Hoseinitabatabaei S., Nati M., Gluhak A., Moessner K. ACM Computing Surveys48 (4):1-52,2016.Type:Article
Date Reviewed: Jul 20 2016

If you want to learn about mobile social signal processing (SSP), a field with the aim of detecting social behavior automatically and in a nonintrusive manner by exploiting the data provided by the multiple sensors embedded in mobile devices, this survey is a must-read.

An introduction to the field presents the three levels of abstraction in the process of extracting and understanding social behavior, and describes a general procedure that starts from sensor data, proceeds with the recognition of social interactions (who is interacting with whom), continues with the extraction of behavioral cues and their mapping into social signals, and finally the inference of social behaviors. Most of the remainder of the paper is a thorough analysis of the state of the art for each of these stages.

First, sensing frameworks are analyzed with the goal of providing the reader with criteria for selecting an appropriate framework for a given social behavior application, like energy consumption, privacy preservation, or software licenses.

Then, different approaches to social interaction detection are described, from those based just on proximity to those that combine several modalities. Complexity, unobtrusiveness, and detection errors are the main factors to be considered for this step.

Next, the survey tackles the extraction of behavioral cues, classified as auditory, physical activity, gestures, head and body posture, facial expressions and eye tracking, space and environment, device usage, and physiological cues. Many solutions have been proposed to perform this process, being the most mature aspect of the mobile SSP field.

Mining social signals from behavioral cues and inference of social behavior are much less mature aspects, with contributions mainly in the inference of stress, emotion, mood, personality traits, and dominance.

The last part of the survey outlines the main application areas of mobile SSP (healthcare, organizational engineering, and marketing), followed by a brief summary of the current state of the field and a list of the main challenges that still need to be addressed by researchers.

Every aspect of the area is carefully and extensively examined in a quite long but very well structured survey that allows people with different backgrounds and levels of expertise to benefit from reading it. More than eight pages of references and pointers to additional surveys are provided for readers who want to go even deeper into some issues.

Reviewer:  Angelica de Antonio Review #: CR144608 (1610-0758)
Bookmark and Share
 
Sensor Networks (C.2.1 ... )
 
 
Sensors (I.2.9 ... )
 
 
Group And Organization Interfaces (H.5.3 )
 
Would you recommend this review?
yes
no
Other reviews under "Sensor Networks": Date
Performance analysis of opportunistic broadcast for delay-tolerant wireless sensor networks
Nayebi A., Sarbazi-Azad H., Karlsson G. Journal of Systems and Software 83(8): 1310-1317, 2010. Type: Article
Nov 8 2010
Heartbeat of a nest: using imagers as biological sensors
Ko T., Ahmadian S., Hicks J., Rahimi M., Estrin D., Soatto S., Coe S., Hamilton M. ACM Transactions on Sensor Networks 6(3): 1-31, 2010. Type: Article
Jan 10 2011
Efficient clustering-based data aggregation techniques for wireless sensor networks
Jung W., Lim K., Ko Y., Park S. Wireless Networks 17(5): 1387-1400, 2011. Type: Article
May 8 2012
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy