When networking meets sociology

Context : Todays’ smart handheld devices allow heterogeneous free data gathering of human surrounding environment and networking usage patterns anytime and anywhere. Hence, an unprecedentedly large amount of human sensory data (i.e., the Big Data era) can be collected and processed: opening ways to connect people, technology, and business. This big data implies advanced knowledge of humans’ behaviour and interactions at a planetary scale and can help tackle networking challenges when used correctly. As our lives become more dependent on connectivity, it is easier to see that people have become eager to engage with mobile applications and connected services [1,2]. Still, as more mobile-connected devices enter the market, the way people, processes, data, and things intelligently connect – the Internet of Everything (IoE) – will change everything about how we use/interact to the network and live our lives. Only technological advances will not be enough to deal with the new emerging challenges imposed by IoE. The ability to understand people behavior and to develop models across complex, interconnected systems is at the core of the required ability to uncover new insights and solutions in the IoE. Nevertheless, there is still a big gap between the way networking solutions are designed (e.g., usually limited to the needs of service providers or types of application) and the everyday behavior or needs of users. Many of them are designed to adapt to network conditions (e.g., physical link conditions, topology changes) and are protocol or service specific (e.g., successful delivery of messages, geographical network coverage). Hence, they are very often oblivious to users behavior and current needs.

MIssion: Thus, the main goal of this Post-Doctoral research is to improve network perception of users surrounding and behavior, allowing then the design of more tactful networking systems (i.e., to add perceptive senses to the network, by assigning it with the human like capabilities of observation, interpretation, and reaction to daily life features and involved entities). For this, we need to understand (1) how, where and for what they are used, (2) how the uses of smartphones vary, as well as (3) how the psycho-social behavior of smartphone usage operates.

Work description: Current knowledge is fragmented because of the tendency of previous research to focus on: i) the study of specific behavior of smartphone use (ignoring thus complex interactions between behaviors), ii) small-N data on specific features of smartphone use, and iii) disciplinary-specific perspectives.

Building on that knowledge, this Post-Doctoral research aim at:

• first, to contribute a uniquely comprehensive account that improves on each of the above limitations. This is possible with the help of an original and extensive smartphone usage datasets that we plan to analyze. This involves tasks related to dataset processing, enrichment and modeling as well as data analysis and knowledge extraction from considered datasets.
• second, tactful networking has its basis on the capability of predicting (e.g., mobility, interests, type and demand of content, a person openness to new experiences and information, etc). Nevertheless, a particularity of predictive models is their over-reliance on past events and trends to predict future ones. Hence, one drawback is their inability to predict new behavior or uncertain events (e.g., predicting new places or changes in users’ trajectories in case of random events) or still to capture the “exploration to new things” aspect of human. Building on the extracted knowledge described here above, this Post-doc research aim then to model the exploration pattern of people (i.e., some people are more prone to present uncertain behavior than others). The exploration pattern will thus feed our predictions models and better adjust accuracy.

Requirements: Candidates are expected to have a strong background in one or more of the

following fields: mobile communication networks, data mining, machine learning, statistical analysis, clustering algorithms, context and content modeling, algorithm design and implementation, scripting.

Requirements for this position also include:

• a PhD in a field related to the position topic
• an outstanding publication record in top-tier conference and journals
• fluency in written and spoken English.

Applications including a CV and recommendation letters of two referees shall be sent by email to aline.viana@inria.fr. Applications will be evaluated until the position is filled.

Applications: Candidates have to provide the following documents to be considered at the selection procedure:

• CV
• publication list and 2 full publications (representative of the candidate work)
• motivation letter (explaining why the selected topic, how do you think you can fit the topic, what are your motivations for the topic compared to your previous work, etc)
• 2 recommendation letters
• perspective of professional insertion after the post-doc

References:

[1] Cisco. Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, 2016–2021 White Paper, 2014–2019. March 2018.

[2] Rivera J. and Meulen, R. van der. Gartner Says Annual Smartphone Sales Surpassed Sales of Feature Phones for the First Time in 2013. English. Gartner. Feb. 2013. url: http://www. gartner.com/newsroom/id/2665715.