The Digital Communication Methods Lab, an initiative of the RPA Communication, renewed its support to a series of innovative research projects focused on substantive and methodological development for communication science research in partnership with Amsterdam School of Communication Research (ASCoR) members.

After three successful rounds in 2018, 2019, and 2020,  five new projects have been selected to receive funding for 2021 and complement ongoing activities at the lab.


Automated content analysis

Personality and susceptibility to political microtargeting: a machine-learning approach based on Twitter text

by dr. Brahim Zarouali and dr. Tom Dobber

This project will adopt psychological profiling by predicting consumers’ personality based on their text from Twitter; this will be done with a machine learning (ML) algorithm. In addition, we will aim is to investigate the validity of this personality classifier. This will be achieved by comparing the algorithmic scores to self-reported personality scores. Taking the self-report as a golden standard, we will be able to draw conclusions regarding the accuracy and validity of the algorithm in predicting people’s personality based on social media data. As such, it can prove to be a valid substitute for personality assessment.


Age and gender bias in AI-driven recruitment: Modelling the influence of hidden features on the ranking of job candidates

by dr. Anne Kroon and dr. Toni van der Meer

Algorithms are fundamentally transforming how organizations recruit job candidates. The current project aims to investigate the extent to which algorithmically-driven resume search engines inhibit or facilitate gender and age inequality in the recruitment process. The novelty of the project lies in tracing the influence of hidden (in addition to manifest) features that may implicitly signal social membership, such as variations in writing style, work experience, and hobbies listed. The potential for inequality is especially critical for hidden features—as they are arguably more difficult to identify and may therefore affect ranking despite explicit efforts to debias training data and algorithms.


Media Exposure

Opening the targeting black box: vulnerability exploitation through personalization

by dr. Hilde Voorveld, dr. Corine Meppelink, Joanna Strycharz, and dr. Brahim Zarouali

While data-driven personalization strategies are present in all areas of online communication, their impact on individuals and society is still not fully understood. Ongoing debates about online targeting are often emotion-driven and based on assumptions what algorithms might and could do in terms of impact on users. The proposed project focuses on targeting mechanisms on Facebook and investigates their impact on different types of users. Drawing on theories on digital vulnerabilities, we investigate if social media targeting may lead to vulnerability exploitation, and whether this differs between certain user groups for example due to different coping strategies applied by individuals.


Mobile Communication

Simply irresistible? Towards a methodological conceptualization of smartphone interruptions

by dr. Susanne Baumgartner, dr. Jakob Ohme, and dr. Sindy Sumter

Smartphones have become an integral part of our daily routines. In many instances smartphone use sessions are initiated through external triggers, such as push notifications. However, frequently smartphone sessions are also self-initiated through so-called internal triggers (e.g. curiosity; fear of missing out). To date, we lack an understanding to what extent smartphones interrupt our daily activities, and whether these interruptions are more frequently internally or externally triggered. Moreover, very little is known about the spatial and temporal conditions of smartphone interruptions, and their effects on user stress, procrastination, and well-being. For this reason, the current 14-day study will empirically conceptualize the types and dynamics of smartphone interruptions using an innovative methodological approach that combines the usage of smartphone activity tracking and surveys within one smartphone app.


Physiological stress responses to receiving smartphone notifications during task performance

by dr. Monique Alblas, dr. Eline Smit, and dr. Bert Bakker

Physiological stress responses to receiving smartphone notifications during task performance
In today’s world, the use of digital communication technologies has become an integral part of our private and working lives. This ‘permanent state of connectedness’ has been proposed to contribute to a range of mental health related outcomes, such as increased stress, anxiety, and depression. However, longitudinal studies have shown very little evidence for the existence of an association between screen time and mental health. This may not be surprising, given that this relationship is likely highly depending on the situational context. In an experimental study, we aim to investigate physiological stress responses to receiving smartphone notifications while performing a high vs. low cognitively demanding task. We also explore to what extent these physiological responses correlate with psychological, self-reported measures that retrospectively assess experienced stress.