This paper explores how the portrayal of female characters in fanfiction evolved in response to the #MeToo movement and fourth-wave feminism, with the aim of assessing whether the impact of the awareness of the campaign was broad enough to visibly alter how the average author portrays women in narrative contexts. To analyze these trends, fanfiction data from Archive of Our Own (AO3) spanning 2015–2019 was parsed, and two Natural Language Processing (NLP) pipelines — Word2Vec and GloVe, and BERT — were developed. The study finds that bias scores, aggregated through formulas created to compare gendered associations, show a stronger stereotypization of women before 2017 compared to after. Furthermore, a similar trend is discovered in the representation of women in fanfiction. While the BERT pipeline proved most effective for capturing contextual nuances, it is significantly limited by its reliance on binary labels and computational intensity. This further indicates the need for more inclusive and sustainable methods, making the Word2Vec/GloVe models more appropriate for this task. The paper concludes with recommendations for future work, including broader representation, longer-term analysis, and enhanced detection of evolving language patterns.

The introduction of Pretrained Language Models (PLMs) has revolutionised the field of Natural Language Processing (NLP) and paved the way for many new, exciting large-scale studies for various areas of research. One such field presents itself in the emerging digital literary corpus that is fanfiction, providing research opportunities within the fields of (NLP), Computational (Socio-) Linguistics, the Social Sciences and Digital Humanities. However, because of the unique linguistic characteristics of this literary domain many modern NLP solutions utilizing PLMs encounter difficulties when applied on fanfiction texts. This paper aims to indicate that the performance of various NLP tasks performed by PLMs on fanfiction texts can be improved by applying Domain Adaptive Pre-Training (DAPT) to PLMs. A case-study is performed to show that the performance of a BERT-based PLM can be improved for the downstream NLP task of Named Entity Recognition (NER) by applying supervised domain specific fine-tuning. While we gain a 6% increase in F1 score performance, we are sceptical about these results due to the limited amount of annotated data available leading to the model overfitting and show a lack of capacity to generalize to unseen data from the CoNLL NER dataset.

This study investigates how genre preferences and sentiment influence fanfiction popularity across multiple languages, focusing on English, Mandarin, Russian, and Spanish datasets. Leveraging advanced natural language processing techniques, including multilingual sentiment analysis, genre classification, and topic modeling, this research explores the interplay between cultural and linguistic factors in storytelling. Preprocessing steps, such as translation and named entity recognition, ensured consistency and reduced noise across the multilingual dataset. Key findings reveal cross-linguistic patterns, such as the popularity of genres like Alter- nate Universe and Romance, alongside cultural distinctions in sentiment and engagement. This work contributes to computational fan studies by demonstrating how linguistic and cultural factors influence storytelling trends and audience preferences in fanfiction.

Natural language processing, specifically style, is not explored significantly in the context of fan-fiction. By using function word frequency analysis, this paper explores the similarity in style between original works and fan-fictions derived from them as well as the impact of those stylistic similarities on the fan-fictions' successes. Investigating the works of Worm and Narnia and utilising a control set, this hypothesis is examined. Similarity in style seems to be variable, but it is suggested that certain stylistic features lead to success more than other regardless of the original work's style. More research would be needed to confirm those numbers.

Fanfiction writers always look for ways to make their stories more engaging. Analyzing what influences the popularity of fanfiction provides insights into readers' preferences and allows writers to tailor to these. This paper attempts to find linear correlations between fanfiction stories and the emotional journey of their characters. It does so by computationally extracting these journeys from 319 Good Omens fanfiction stories, defining and extracting several features from them and using simple linear regression to determine their correlation to fanfiction popularity. Five features were found to have a significant influence on fanfiction popularity. It was also determined that readers prefer characters that have low emotional fluctuations in their behavior.

This research investigates the detection of gestures using a torso-worn accelerometer sensor. Using the Conflab dataset, we focus on gestures during conversations in mingling scenarios. Due to significant variability in gesture styles among individuals, traditional methods face challenges in building personalized models. Our experiments demonstrate that Transductive Parameter Transfer (TPT), an adaptive transfer learning method, can more effectively model these individual differences in gesturing. To gain insights into individual expressiveness, we classify gestures into three classes: 'no gesture,' 'normal,' and 'large' gestures. TPT performed an average AUC score of 0.84 in binary classification and 0.77 in multiclass classification. These findings highlight the potential of using a single torso-worn accelerometer to understand social behavior in naturalistic settings.

Multiactivity analysis investigates one's coordination of actions within a social context, such as gestures and speech, usually using video recordings of the social activity, to further understand the rules of human behaviour. This paper focuses specifically on the coordination between speaking and drinking activities within a social setting, and explores the possibility of automatically identifying these events using audio captured from a drinking glass. As social interactions occur in vastly different contexts, this paper also investigates the effect that background noise might have on the accuracy of identifying these events. Different parameters and audio features were compared. Linear classification models LR and SVM with a linear kernel were able to achieve 100% accuracy for all sample lengths between 2 and 8 seconds using the first 20 PCA components from 60 audio features. The best performing feature in identifying speaking and drinking events was MFCCs, achieving an F₁ score of 99.4% on average across models with a training sample length of 3 seconds. Background noise had different effects on classification accuracy depending on the type, with music lowering the F₁ score to 74.3%, noisy room audio to 64.7%, and podcast audio simulating the presence of other speakers to 59.6% using MFCCs and a 3-second sample length

Human activity recognition plays an interesting and important role nowadays as there are a variety of use cases. It is utilized in health monitoring, in the development of human-computer interaction system and in security monitoring. However current methods involve usage of privacy sensitive data and impractical sensors for everyday usage. To tackle this problem, we aim to answer the research question "How to maximize the capabilities of in-mouth sensors for human activity recognition?". The main contributions of this paper are the classification of different gestures using an in-mouth device, implementation of a classifier directly onto a microcontroller and the evaluation whether the models can generalize to multiple people. To investigate this, we experimented with popular classical machine learning classifiers: Decision Tree, K-Nearest Neighbors, Support Vector Machine, Logistic Regression and Random Forest classifiers. The results shows that the F1-score of all classification problems are above 80% using the various classifiers along with different parameters.

Understanding how users retrospectively evaluate their interactions with adaptive intelligent systems is crucial to improving their behaviours during interactions. Prior work has shown the potential to predict retrospective evaluations based on different real-time aspects of conversations, such as verbal cues and non-verbal behaviours. However, the relationship between how one retrospectively evaluates and the real-time evaluations in the moment of conversations remains unclear. This study investigates the relationship between real-time evaluations of a situation, using the Situational Interdependence Scale (SIS) framework, and its retrospective evaluations. We investigate the presence of the peak-end rule and a complex relationship that could be modelled using Long Short-Term Memory (LSTM) for each SIS dimension using the PACO dataset. Due to the absence of ground truth for real-time SIS evaluations, we also present a methodologically sound technical approach to utilize a Large Language Model (LLM) to estimate values for each SIS dimension for each spoken utterance in conversations. Analysis of the experiments revealed the absence of both the peak-end rule and an LSTM-modelled relationship across all dimensions of SIS. However, both types of models at least predict better than the average of the estimated real-time evaluation. This may be largely due to the inaccuracy of the estimated real-time SIS evaluations and the limited LLM’s capability of labelling real-time SIS in conversational data. Future works may focus on improving the annotation of real-time SIS evaluations through human annotation or human-supervised few-shot learning of LLM, using other modalities in combinations with verbal content, and exploring other predictive models.

Hand gestures play a crucial role in communication, especially in social interactions. This research investigates the viability of using coding schemes to describe hand gestures and how accurately they can be classified in crowded environments by using fine-tuned visual transformers such as VideoMAE. The dataset used during training is based on the Conflab dataset and contains top-view video recordings of social interactions in a crowded social setting. The videos are manually annotated for gesture phases (preparation, hold, stroke, recovery) and gesture units. The two classifiers obtain high accuracies after fine tuning, with an overall accuracy of 95% for the gesture phase classification and 93% for classifying whether a clip is a gesture unit or not. These findings suggest that the proposed approach is effective in crowded environments and can be adapted for real-time applications.

Researching hand gestures in real-world social interactions requires very careful analysis. While gesture coding schemes were created with that purpose in mind, they are not widely utilised in research. Moreover, studies on gesture classification rarely focus on the physical nature of movements involved in gesturing, despite the fact that being able to quantify the motion could reveal useful patterns and correlations. To address those points, this research proposes the following approach: using machine learning models to automatically classify physical features of hand gestures, according to a coding scheme. Two such classifiers were created, for the left and right hand respectively. Overall, the results are quite promising - despite a small and imbalanced training set and complex features both models achieved an accuracy of roughly 60%. Moreover, the results indicate that by avoiding some of the simplifications that this research makes, and by using more balanced training data, the accuracy could be significantly increased. This is concrete evidence that machine learning models can indeed be used to classify the physical aspects of hand gestures, as defined
by a coding scheme, in social interactions in the wild.

In the scientific community, a few prominent researchers, known as "superstars," receive most of the attention, citations, and resources. However, it is unclear whether they promote true innovation. This study replicates and extends previous work analyzing how superstars influence their collaborators, focusing on the field of computer science. Using the Semantic Scholar Academic Graph dataset, we confirm that while connected researchers in computer science tend to publish more and receive more citations, their ideas are often less innovative. Unlike in the work we replicate, however, we observe this effect even before dissociating the connected researchers from superstars. We also develop a new metric to further clarify the impact of superstars on research diversity. The findings provide insights into the role of superstars in scientific innovation.

This study introduces a new metric for evaluating the disassociation between superstar and non-superstar researchers. Superstar researchers are defined as those in the top 0.1\% by h-index. Leveraging a large dataset, this paper analyzes the data and aims to flatten the discrepancy between superstars and non-superstars, in terms of innovation and popularity. Some authors that publish innovative papers and who haven't collaborated with superstars, tend to be left in the shadows, compared to the ones that have collaborated with superstars from an early stage. The new metric indicates the disassociation between such authors, by factoring in certain parameters that were put into perspective with the help of a Multiple Linear Regression model. The findings reveal significant differences in dissociation scores between researchers and superstar researchers, offering new insights into the dynamics of academic innovation and collaboration. This metric provides a robust tool to identify where an author stands in terms of dissociation and what needs to be done to diminish the discrepancy.

Superstar researchers - those who author research papers which are far more widely cited than average - are generally well-respected within their fields and are frequently sought by new researchers for advice on career development and for collaborations. Though the effect of collaboration with superstar researchers on associated researchers is not well-researched yet, it is believed that collaboration with superstar researchers increases the research output of associated researchers, but may decrease their originality and innovation. This project explores a method of visualizing the career development of researchers associated with superstars. Using a dataset of authors, papers, and paper citations, a graph has been created with papers as edges and nodes as authors to visualize the career development of associate authors after collaboration with a superstar. The utility of this visualization is evaluated using heuristics.

This paper presents a smart drinking cup proto- type platform for social sensing studies. Recording the dynamics of unscripted human interactions in social settings can be challenging and often requires the participants to wear external hardware. This leads to greater participant discomfort and behavioural changes. To address this, we propose a prototype for a smart sensing cup: a multi-sensor data collection device integrated into a drinking cup. A hydrostatic pressure sensor is used for the volume and temperature measurements of the con- tents of the cup. Orientation data is gathered with a three-axis accelerometer, measuring the pitch of the cup. Detection of whether the cup is being held by a participant is ensured using a capacitance sensor. The sampling rate for all sensors is 10 Hz and can store up to an hour of data on the device. Using the sensor data we are able to detect whether a cup is being held, identify drinking events and fluid intake and give live feedback on this using an LED.

Understanding children's social interaction patterns is critical for their cognitive development; however, existing psychological studies often focus on dyadic interactions, overlooking the complexities of group dynamics. This study extends the concept of homophily—the tendency for individuals to interact with similar others—by exploring its implications within group settings. We introduce F-formations, a well-adopted notion from the computational field for detecting interaction groups in adults, which has yet to be extensively studied in children. By identifying this research gap, we aim to investigate how F-formations can be applied to children's social interactions.
Our case study was conducted in a preschool setting, specifically in the Starfish classroom, which includes children with hearing loss. Several key findings emerged from this study. First, we observed that F-formations can be detected in children's interactions, though some formations violate the definition of F-formations. Second, while the homophily effect was not evident in dyadic studies concerning children's hearing conditions, it was observed in group settings. We found that children prefer to form more homogeneous and smaller groups, with those who have hearing loss spending more time with peers who share similar characteristics. Overall, our results suggest that integrating group interaction data into traditional dyadic analyses provides valuable insights into children's social behavior, highlighting the importance of studying group dynamics alongside dyadic interactions.

Detecting nearby vehicles involves utilizing data from various sensors installed on a car as it moves. Common sensors for identifying nearby vehicles include LiDAR, cameras, and RADAR. However, all of these sensors suffer from the same issue -- they cannot detect an approaching vehicle that is not yet visible. Hence, this thesis explores the potential of using a microphone array -- an array of sensors capable of detecting vehicles that are out of sight. Exploring prior research on detecting obstructed vehicles using sound reveals an existing model capable of detecting nearby vehicles approaching from behind blind corners. However, as the local geometry around the ego vehicle affects the perceived sound patterns, this model was only designed to work within a specific set of T-junctions. Therefore, the thesis aims to take a step further and develop a detection model capable of detecting vehicles behind blind corners in environments not included in the training set of the deployed model. This is challenging for multiple reasons. First, literature review revealed a lack of suitable datasets comprising sounds from approaching vehicles behind blind corners within various road junctions. In addition, microphones, like other sensors, come with limitations. Sound inherently provides less spatial information compared to commonly used sensors in autonomous driving, such as LiDAR or cameras. Considering sound propagation variations in different road junction geometries, building a model adaptable across diverse junction types presents a challenge. To overcome the data scarcity and sound's inherent spatial limitations, the study investigates the potential of employing simulated acoustic responses within artificial road environments as training data for real-world vehicle detection. Simultaneously, to complement the sounds inherent advantage of detecting objects that are out of sight, the thesis proposes to use a Bird's Eye View (BEV) encoding of the top-down map from the driving vehicle's perspective. Having an encoding of the top-down map of the current driving environment would allow a detection model to expect sound signatures commonly observed within a given setting. Overall, the assessment of acoustic simulations could not outline a singular configuration of simulation properties allowing realistic sound propagation for any kind of considered junctions when hearing an approaching vehicle. However, it was observed that the utilization of specific simulation parameters can result in realistic sound propagation within the given junction. Subsequently, evaluating a novel BEV encoding within the newly proposed acoustic detection pipeline demonstrated either equivalent or superior performance compared to a model relying solely on sound. Overall, this research underscores the potential of incorporating BEV encoding in non-line-of-sight acoustic detection and suggests the promise of acoustic simulations within the field. This study contributes to advancing the integration of sound as an additional data modality in vehicle detection.

Endowing machines with social competence is not only a science fiction theme. It is also a long-held goal in computer science. Machines have changed how we work, communicate, and do art, science, and engineering, but they have had little effect on one of our core human needs: social interaction. Although digital communication has changed the way we interact with others, machines have arguably done little to enhance the quality of our face-to-face interactions and are seldom seen as tools to help us improve the way we interact with others. This is in part due to their lack of social competence thus far.

A crucial stepping stone towards social competence and the ability to display empathy is the ability to assess social experience. Social experience refers to internal states reflecting an individual's perception of a social situation, like enjoying a conversation or feeling attracted to someone they are interacting with. Social experience variables are hard to study because they are not directly observable and change over time. Researchers must rely on self-reports or third-party assessments (annotations). Algorithms for assessment of social experience generally take one of two approaches: 1) Direct modeling of the relationship between raw/derived signals and experience variables, utilizing sensor readings or outputs of detectors and feature extractors; and 2) intermediate modeling/detection of discrete actions performed during interactions (ie. speaking, laughter, gesturing).

In this thesis dissertation, we focus on in-the-wild mingling setting, where subjects are standing and are free to form and switch conversation groups as they desire. Data collection and annotation are paid special attention due to their relevance in a nascent field and the nuance involved in collecting and annotating social signals. Because the goal is to study machine social perception in real-life settings, interactions are not scripted and instrumentation is kept to a minimum.

We start with work concerned with the direct assessment of social experience, in this case of attraction, by exploring the predictive power of body acceleration. By analyzing accelerometer data from speed dating interactions, we investigate how the intensity and variations in body movement relate to self-reported attraction levels. This study sheds light on the predictive power of synchrony, mimicry, and convergence estimates for predicting attraction, and potentially other constructs related to affiliation.

We then address the detection of speaking, an action of wide interest in social signal processing due to the relevance of turn-taking in social experience. We address the limitations posed by visual cross-contamination in crowded mingling settings. We introduce a model that employs accelerometer readings and body poses to enhance the robustness of speaking status detection in a complex scene, with multiple interactions occurring simultaneously.

The dissertation also presents two novel datasets: ConfLab and REWIND, each serving a unique purpose. ConfLab, collected during a conference, is notable for its annotations of body joints, and improvements to the sensor setup resulting in increased data fidelity. Such methodological contributions to enable efficient and high-quality data collection are increasingly valuable given the scarcity of social interaction datasets, particularly in mingling settings. REWIND, gathered at a business networking event, stands out with its high-quality individual audio recordings, useful for the cross-modal study of multimodal signals such as speaking or laughter.

In a similar line, we present the Covfee software framework. Covfee challenges existing annotation methodologies by introducing and studying interfaces for continuous annotation for keypoints and actions. This framework was instrumental in efficiently processing the vast amounts of data collected in studies like ConfLab by streamlining the annotation process.

Also building on the Covfee framework, the dissertation culminates in an exploration of laughter annotation across different modalities. By comparing laughter annotations acquired in different conditions, the research highlights the complexities and nuances involved in interpreting social signals across different sensory inputs. We challenge the assumption that laughter intensity should be considered a property of the laughter episode. Instead, we find evidence that laughter evaluations differ significantly depending on the modalities available to the observer and that modalities with higher agreement will not necessarily result in the highest model performance. These results not only contribute to the study of laughter detection but also provide valuable insights for future research on multimodal social signal processing.

In summary, this dissertation weaves together a series of methodological contributions and novel findings, often derived from these new methods, each contributing to further our understanding of how to best train machines for social understanding and competence.@en

This research aims to answer the question whether non-verbal vocal behavior can be used to estimate intention to speak. To answer this question data from a dutch social networking event is used to gather intentions to speak. The intentions to speak are split up in two categories: successful and unsuccessful intentions. The unsuccessful intentions are further split up into two categories: unsuccessful intentions to start speaking and unsuccessful intentions to continue speaking. The perceived unsuccessful intentions to speak are gathered by manually annotating a 10-minute segment of the networking event and successful intentions to speak are automatically extracted using Voice Activity Detection. From the audio, non-verbal vocal features are extracted to train a machine learning model to predict if there is an intention to speak. The model is trained on successful intentions to speak and evaluated on both successful and unsuccessful intentions to speak. From the experiment results it was concluded that the model predicted intention to speak better than random guessing.

This research paper implements, evaluates, and compares two approaches, a machine learning (ML) approach and a rule-based approach, aimed to estimate intentions to speak. The ML approach trains lexical information extracted from time windows surrounding speech events. The rule-based approach looks for specific keywords or utterances to identify intentions to speak. The results show that the ML approach is a more favourable solution to the problem due to its adaptability and potential for improvement. Sample generation and parameter tweaking showed to be vital to the performance of the model, with its best performance being when it predicted unsuccessful intentions to continue speaking. This study concludes that a machine learning approach can be a viable solution for estimating intentions to continue speaking, with there being future use cases in conversational systems and human-computer interactions.