Videoconference interviews are now integral to many selection processes. Theoretical arguments and empirical findings suggest that videoconference interviews may lead to different interview performance ratings in comparison to Face-to-Face (FTF) interviews. This has led to the question of the comparability of the psychometric properties of videoconferences and FTF interviews. However, evidence from actual selection processes stems from the beginning of the century, and recent findings predominantly stem from simulated interview contexts. We present insights from an actual selection process within a large European organization where we had the unique opportunity for a quasi-experimental investigation of differences between videoconference and FTF interviews. Initially, the organization conducted FTF interviews, and after the onset of the COVID-19 pandemic, the interviews were conducted via videoconference. We examine mean differences in applicant performance ratings and evidence for response format-related validity differences. There were only small, non-significant mean differences and no evidence for response format related validity differences. We discuss possible causes for discrepancies in our findings compared to previous research. Furthermore, we conclude that downstream consequences of differences between FTF and videoconference interviews may be lower than previously expected. We end with a call for research on the interaction between technology-design and selection-tool-design features.@en

Developments in the field of Artificial Intelligence (AI), and particularly large language models (LLMs), have created a 'perfect storm' for observing 'sparks' of Artificial General Intelligence (AGI) that are spurious. Like simpler models, LLMs distill meaningful representations in their latent embeddings that have been shown to correlate with external variables. Nonetheless, the correlation of such representations has often been linked to human-like intelligence in the latter but not the former. We probe models of varying complexity including random projections, matrix decompositions, deep autoencoders and transformers: all of them successfully distill information that can be used to predict latent or external variables and yet none of them have previously been linked to AGI. We argue and empirically demonstrate that the finding of meaningful patterns in latent spaces of models cannot be seen as evidence in favor of AGI. Additionally, we review literature from the social sciences that shows that humans are prone to seek such patterns and anthropomorphize. We conclude that both the methodological setup and common public image of AI are ideal for the misinterpretation that correlations between model representations and some variables of interest are 'caused' by the model's understanding of underlying 'ground truth' relationships. We, therefore, call for the academic community to exercise extra caution, and to be keenly aware of principles of academic integrity, in interpreting and communicating about AI research outcomes.

@en

So far, the relationship between open science and software engineering expertise has largely focused on the open release of software engineering research insights and reproducible artifacts, in the form of open-access papers, open data, and open-source tools and libraries. In this position paper, we draw attention to another perspective: scientific insight itself is a complex and collaborative artifact under continuous development and in need of continuous quality assurance, and as such, has many parallels to software artifacts. Considering current calls for more open, collaborative and reproducible science; increasing demands for public accountability on matters of scientific integrity and credibility; methodological challenges coming with transdisciplinary science; political and communication tensions when scientific insight on societally relevant topics is to be translated to policy; and struggles to incentivize and reward academics who truly want to move into these directions beyond traditional publishing habits and cultures, we make the parallels between the emerging open science requirements and concepts already well-known in (open-source) software engineering research more explicit. We argue that the societal impact of software engineering expertise can reach far beyond the software engineering research community, and call upon the community members to proactively help driving the necessary systems and cultural changes towards more open and accountable research.@en

Machine Learning (ML) models influence all aspects of our lives. They also commonly are integrated in recommender systems, which facilitate users’ decision-making processes in various scenarios, such as e-commerce, social media, news and online learning. Training performed on large volumes of data is what ultimately drives such systems to provide meaningful recommendations. However, a lack of standardized practices has been observed when it comes to data collection and annotation methods for ML datasets. This research paper systematically identifies and synthesizes the state of standardization with regard to data collection and annotation reporting in the recommender systems domain, through a systematic literature view into the 100 most-cited recommender systems papers from the most impactful venues within the Computing and Information Technology field. Multiple facets of the employed techniques are touched upon, such as reported human annotations and annotator diversity, label quality, and the public availability of training datasets. Recurrent use of just a few benchmark datasets, poor documentation practices, and reproducibility issues in experiments are some of the most striking findings uncovered by this study. We discuss the necessity of transitioning from pure reliance on algorithmic performance metrics to prioritizing data quality and fit. Finally, concerns are raised when it comes to biases and socio-psychological factors inherent in the datasets, and further exploration of embedding these early in the design of ML models is suggested.

@en

This article is based on conversations from the project “Big Data in Psychological Assessment” (BDPA) funded by the European Union, which was initiated because of the advances in data science and artificial intelligence that offer tremendous opportunities for personnel assessment practice in handling and interpreting this kind of data. We argue that psychologists and computer scientists can benefit from interdisciplinary collaboration. This article aims to inform psychologists who are interested in working with computer scientists about the potentials of interdisciplinary collaboration, as well as the challenges such as differing terminologies, foci of interest, data quality standards, approaches to data analyses, and diverging publication practices. Finally, we provide recommendations preparing psychologists who want to engage in collaborations with computer scientists. We argue that psychologists should proactively approach computer scientists, learn computer scientific fundamentals, appreciate that research interests are likely to converge, and prepare novice psychologists for a data-oriented scientific future.@en

Psychology research has shown that song lyrics are a rich source of data, yet they are often overlooked in the field of MIR compared to audio. In this paper, we provide an initial assessment of the usefulness of features drawn from lyrics for various fields, such as MIR and Music Psychology. To do so, we assess the performance of lyric-based text features on 3 MIR tasks, in comparison to audio features. Specifically, we draw sets of text features from the field of Natural Language Processing and Psychology. Further, we estimate their effect on performance while statistically controlling for the effect of audio features, by using a hierarchical regression statistical model. Lyric-based features show a small but statistically significant effect, that anticipates further research. Implications and directions for future studies are discussed.

@en

Self-control is a crucial factor in maintaining an established romantic relationship, but its role in relationship formation is understudied. The current study tested whether trait self-control is related to a more selective approach toward romantic partners. Over 4 years, we organized 11 speed-date events at which a total of 342 single, heterosexual participants met potential partners. Our results indicated that there was no main effect of self-control on selectivity. However, there was an interaction between self-control and sociosexual orientation (SOI) in predicting selectivity. Specifically, self-control was positively related to selectivity for people with a restricted SOI (i.e., interested in a long-term, stable relationship). For people with an unrestricted SOI (i.e., interested in a short-term, sexual relationship), however, self-control was related to lower selectivity. Our findings point to the flexibility of self-control in facilitating goal progress, stimulating people to refrain from—or act on—their impulses, depending on their own personal mating goals.

@en

There is evidence that testosterone and cortisol levels are related to the attraction of a romantic partner; testosterone levels relate to a wide range of sexual behaviors and cortisol is a crucial component in the response to stress. To investigate this, we conducted a speed-dating study among heterosexual singles. We measured salivary testosterone and cortisol changes in men and women (n = 79) when they participated in a romantic condition (meeting opposite-sex others, i.e., potential romantic partners), as well as a control condition (meeting same-sex others, i.e., potential friends). Over the course of the romantic speed-dating event, results showed that women's but not men's testosterone levels increased and cortisol levels decreased for both men and women. These findings indicate that men's testosterone and cortisol levels were elevated in anticipation of the event, whereas for women, this appears to only be the case for cortisol. Concerning the relationship between attraction and hormonal change, four important findings can be distinguished. First, men were more popular when they arrived at the romantic speed-dating event with elevated cortisol levels. Second, in both men and women, a larger change in cortisol levels during romantic speed-dating was related to more selectivity. Third, testosterone alone was unrelated to any romantic speed-dating outcome (selectivity or popularity). However, fourth, women who arrived at the romantic speed-dating event with higher testosterone levels were more selective when their anticipatory cortisol response was low. Overall, our findings suggest that changes in the hormone cortisol may be stronger associated with the attraction of a romantic partner than testosterone.

@en

Prior research from the field of music psychology has suggested that there are factors common to music preference beyond individual genres. Specifically, research has shown that self-reported ratings of preference for individual musical genres can be reduced to 4 or 5 dimensions, which in turn have been shown to correlate to relevant psychological constructs, such as personality. However, the number of dimensions emerging from multiple studies has varied despite the care taken in conducting such research. Data-driven approaches offer opportunities to further this line of research with actual listening data, at a scale and scope surpassing that of traditional psychological studies. Although listening data can be considered more direct and comprehensive evidence of listening preference, transforming this data into meaningful measurements is non-trivial. In the current paper, we report on investigations seeking to find interpretable underlying dimensions of music taste, using implicit large-scale listening data. Offering a critical reflection on potential researchers' degrees of freedom, we adopt an explicit systematic approach, investigating the impact of varying different parameters, analysis, and normalization techniques. More precisely, we consider various ways to extract listening preference information from two large, openly available datasets of music listening behavior, making use of principal component analysis and variational autoencoders to extract potential underlying dimensions. Results and implications are discussed in light of prior psychological theory, and the potential of user listening data to further research on music preference.@en

Objectives: This study proposes an alternative hypothetical scenario method capitalizing on the potential of virtual reality (VR). Rather than asking participants to imagine themselves in a specific situation, VR perceptually immerses them in it. We hypothesized that experiencing a scenario in VR would increase feelings of being “present” in the situation, and add to perceived realism compared to the written equivalent. This, in turn, was expected to trigger stronger emotional experiences influencing subsequent behavioral intentions. Methods: In an experiment, participants (N = 153), visitors of a large music festival, either read a “bar fight” scenario or experienced the scenario in VR. Following the scenario, they were presented a series of questions including intention to aggress, perceived risk, anticipated shame/guilt, presence, perceived realism, and anger. Analyses were conducted using analysis of variance, stepwise regression, and mediation analysis using nonparametric bootstrapping. Results: In line with expectations, the results indicate significant differences between conditions with the VR scenario triggering stronger presence, higher realism, and higher intention to aggress. Importantly, presence and anger mediated the relation between condition and intention to aggress. Conclusions: We show that the VR scenario method may provide benefits over written scenarios for the study of criminal decision-making. Implications are discussed.

@en

In music information retrieval, we often make assertions about what features of music are important to study, one of which is vocals. While the importance of vocals in music preference is both intuitive and anticipated by psychological theory, we have not found any survey studies that confirm this commonly held assertion. We address two questions: (1) what components of music are most salient to people’s musical taste, and (2) how do vocals rank relative to other components of music, in regards to whether people like or dislike a song. Lastly, we explore the aspects of the voice that listeners find important. Two surveys of Spotify users were conducted. The first gathered open-format responses that were then card-sorted into semantic categories by the team of researchers. The second asked respondents to rank the semantic categories derived from the first survey. Responses indicate that vocals were a salient component in the minds of listeners. Further, vocals ranked high as a self-reported factor for a listener liking or disliking a track, among a statistically significant ranking of musical attributes. In addition, we open several new interesting problem areas that have yet to be explored in MIR.

@en

We present MatchNMingle, a novel multimodal/multisensor dataset for the analysis of free-standing conversational groups and speed-dates in-the-wild. MatchNMingle leverages the use of wearable devices and overhead cameras to record social interactions of 92 people during real-life speed-dates, followed by a cocktail party. To our knowledge, MatchNMingle has the largest number of participants, longest recording time and largest set of manual annotations for social actions available in this context in a real-life scenario. It consists of 2 hours of data from wearable acceleration, binary proximity, video, audio, personality surveys, frontal pictures and speed-date responses. Participants' positions and group formations were manually annotated; as were social actions (eg. speaking, hand gesture) for 30 minutes at 20fps making it the first dataset to incorporate the annotation of such cues in this context. We present an empirical analysis of the performance of crowdsourcing workers against trained annotators in simple and complex annotation tasks, founding that although efficient for simple tasks, using crowdsourcing workers for more complex tasks like social action annotation led to additional overhead and poor inter-annotator agreement compared to trained annotators (differences up to 0.4 in Fleiss' Kappa coefficients). We also provide example experiments of how MatchNMingle can be used.

@en

In a rapidly digitizing world, machine learning algorithms are increasingly employed in scenarios that directly impact humans. This also is seen in job candidate screening. Data-driven candidate assessment is gaining interest, due to high scalability and more systematic assessment mechanisms. However, it will only be truly accepted and trusted if explainability and transparency can be guaranteed. The current chapter emerged from ongoing discussions between psychologists and computer scientists with machine learning interests, and discusses the job candidate screening problem from an interdisciplinary viewpoint. After introducing the general problem, we present a tutorial on common important methodological focus points in psychological and machine learning research. Following this, we both contrast and combine psychological and machine learning approaches, and present a use case example of a data-driven job candidate assessment system, intended to be explainable towards non-technical hiring specialists. In connection to this, we also give an overview of more traditional job candidate assessment approaches, and discuss considerations for optimizing the acceptability of technology-supported hiring solutions by relevant stakeholders. Finally, we present several recommendations on how interdisciplinary collaboration on the topic may be fostered.@en

In this position paper, we take the experimental approach of putting algorithms aside, and reflect on what recommenders would be for people if they were not tied to technology. By looking at some of the shortcomings that current recommenders have fallen into and discussing their limitations from a human point of view, we ask the question: if freed from all limitations, what should, and what could, RecSys be? We then turn to the idea that life itself is the best recommender system, and that people themselves are the query. By looking at how life brings people in contact with options that suit their needs or match their preferences, we hope to shed further light on what current RecSys could be doing better. Finally, we look at the forms that RecSys could take in the future. By formulating our vision beyond the reach of usual considerations and current limitations, including business models, algorithms, data sets, and evaluation methodologies, we attempt to arrive at fresh conclusions that may inspire the next steps taken by the community of researchers working on RecSys.@en

Music has been shown to have a profound effect on lis-teners' internal states as evidenced by neuroscience research. Listeners report selecting and listening to music with specific intent, thereby using music as a tool to achieve desired psychological effects within a given context. In light of these observations, we argue that music information retrieval research must revisit the dominant assumption that listening to music is only an end unto itself. Instead, researchers should embrace the idea that music is also a technology used by listeners to achieve a specific desired internal state, given a particular set of circumstances and a desired goal. This paper focuses on listening to music in isolation (i.e., when the user listens to music by themselves with headphones) and surveys research from the fields of social psychology and neuro-science to build a case for a new line of research in music information retrieval on the ability of music to produce flow states in listeners. We argue that interdisciplinary collaboration is necessary in order to develop the understanding and techniques necessary to allow listeners to exploit the full potential of music as psychological technology.@en