Toxicity in online gaming communities remains a persistent challenge, manifesting across genres, platforms, and player interactions. While much research is focused on in-game toxicity, less is known about how toxic behavior varies between gaming communities on streaming platforms. To address this shortcoming, we analyze approximately 20 million chat messages from 4,452 streams, spanning seven game genres on Twitch. We categorize messages according to Twitch's toxicity taxonomy with a pre-trained Large Language Model using zero-shot classification. The taxonomy comprises four categories and eight subclasses, including harassment, discrimination, sexual content, and profanity. Our approach achieves an F1 score of 94.5

The location to which refugees are assigned upon arrival in a host country is a critical factor for their integration prospects. Several research groups have developed algorithmic tools based on artificial intelligence (AI) to optimize refugee-location matching, with the overall aim of improving refugees’ integration into the labor market. These tools are used in a highly sensitive context, and thus their design, social impacts, and potential long-term consequences need to be systematically assessed. To investigate such effects, we propose an agent-based simulation framework, grounded in sociological theory and real-world survey data. This framework allows for simulating different allocation mechanisms for refugees to locations and studying their impacts on integration outcomes. We illustrate the simulation framework in the German context by comparing the current approach of the Königsteiner Schlüssel (i.e., quasi-random allocation) with algorithm-based matching. We study each procedure’s impact on both economic and social integration and assess structural effects on inequalities between subgroups of refugees. We find that (1) algorithmic assignment can improve both economic and social integration outcomes globally; (2) performance gains vary geographically and demographically, potentially reinforcing existing inequalities; (3) incorporating feedback loops—where each allocation round reshapes local community composition—is crucial for assessing the impacts of algorithmic allocation systems in dynamic social environments.

Balancing games, especially those with asymmetric multiplayer content, requires significant manual effort and extensive human playtesting during development. For this reason, this work focuses on generating balanced levels tailored to asymmetric player archetypes, where the disparity in abilities is balanced entirely through the level design. For instance, while one archetype may have an advantage over another, both should have an equal chance of winning. We therefore conceptualize game balancing as a procedural content generation problem and build on and extend a recently introduced method that uses reinforcement learning to balance tile-based game levels. We evaluate the method on four different player archetypes and demonstrate its ability to balance a larger proportion of levels compared to two baseline approaches. Furthermore, our results indicate that as the disparity between player archetypes increases, the required number of training steps grows, while the model's accuracy in achieving balance decreases.

Applications that store a large number of documents often have summarization and retrieval functionalities to help users digest large amounts of information efficiently. Currently, such systems need to run two task-specific models, for summarization and retrieval, redundantly on the same set of documents. An efficient approach to amend this redundancy would be to reuse hidden representations produced during the summary generation for retrieval. However, our experiment shows that existing models, including recent large language models, do not produce retrieval-friendly embeddings during summarization due to a lack of a contrastive objective during their training. To this end, we introduce a simple, cost-effective training strategy which integrates a contrastive objective into standard summarization training without requiring additional annotations. We empirically show that our model can perform on par or even outperform in some cases compared to the combination of two taskspecific models while improving throughput and FLOPs by up to 17% and 20%, respectively.(1)

The balancing process for game levels in competitive two-player contexts involves a lot of manual work and testing, particularly for non-symmetrical game levels. In this work, we frame game balancing as a procedural content generation task and propose an architecture for automatically balancing of tile-based levels within the PCGRL framework (procedural content generation via reinforcement learning). Our architecture is divided into three parts: (1) a level generator, (2) a balancing agent, and (3) a reward modeling simulation. Through repeated simulations, the balancing agent receives rewards for adjusting the level towards a given balancing objective, such as equal win rates for all players. To this end, we propose new swap-based representations to improve the robustness of playability, thereby enabling agents to balance game levels more effectively and quickly compared to traditional PCGRL. By analyzing the agent's swapping behavior, we can infer which tile types have the most impact on the balance. We validate our approach in the Neural MMO (NMMO) environment in a competitive two-player scenario. In this extended conference paper, we present improved results, explore the applicability of the method to various forms of balancing beyond equal balancing, compare the performance to another search-based approach, and discuss the application of existing fairness metrics to game balancing.

Keywords, that is, content-relevant words in summaries play an important role in efficient information conveyance, making it critical to assess if system-generated summaries contain such informative words during evaluation. However, existing evaluation metrics for extreme summarization models do not pay explicit attention to keywords in summaries, leaving developers ignorant of their presence. To address this issue, we present a keywordoriented evaluation metric, dubbed ROUGE-K, which provides a quantitative answer to the question of - How well do summaries include keywords? Through the lens of this keywordaware metric, we surprisingly find that a current strong baseline model often misses essential information in their summaries. Our analysis reveals that human annotators indeed find the summaries with more keywords to be more relevant to the source documents. This is an important yet previously overlooked aspect in evaluating summarization systems. Finally, to enhance keyword inclusion, we propose four approaches for incorporating word importance into a transformer-based model and experimentally show that it enables guiding models to include more keywords while keeping the overall quality.

Extensive efforts in the past have been directed toward the development of summarization datasets. However, a predominant number of these resources have been (semi)-automatically generated, typically through web data crawling, resulting in subpar resources for training and evaluating summarization systems, a quality compromise that is arguably due to the substantial costs associated with generating ground-truth summaries, particularly for diverse languages and specialized domains. To address this issue, we present ACLSum, a novel summarization dataset carefully crafted and evaluated by domain experts. In contrast to previous datasets, ACLSum facilitates multi-aspect summarization of scientific papers, covering challenges, approaches, and outcomes in depth. Through extensive experiments, we evaluate the quality of our resource and the performance of models based on pretrained language models and state-of-the-art large language models (LLMs). Additionally, we explore the effectiveness of extractive versus abstractive summarization within the scholarly domain on the basis of automatically discovered aspects. Our results corroborate previous findings in the general domain and indicate the general superiority of end-to-end aspect-based summarization. Our data is released at https://github.com/sobamchan/aclsum.

Graph data structures offer a versatile and powerful means to model relationships and interconnections in various domains, promising substantial advantages in data representation, analysis, and visualization. In games, graph-based data structures are omnipresent and represent, for example, game economies, skill trees or complex, branching quest lines. With this paper, we propose G-PCGRL, a novel and controllable method for the procedural generation of graph data using reinforcement learning. Therefore, we frame this problem as manipulating a graph’s adjacency matrix to fulfill a given set of constraints. Our method adapts and extends the Procedural Content Generation via Reinforcement Learning (PCGRL) framework and introduces new representations to frame the problem of graph data generation as a Markov decision process. We compare the performance of our method with the original PCGRL, the run time with a random search and evolutionary algorithm, and evaluate GPCGRL on two graph data domains in games: game economies and skill trees. The results show that our method is capable of generating graph-based content quickly and reliably to support and inspire designers in the game creation process. In addition, trained models are controllable in terms of the type and number of nodes to be generated.

Achieving optimal balance in games is essential to their success, yet reliant on extensive manual work and playtesting. To facilitate this process, the Procedural Content Generation via Reinforcement Learning (PCGRL) framework has recently been effectively used to improve the balance of existing game levels. This approach, however, only assesses balance heuristically, neglecting actual human perception. For this reason, this work presents a survey to empirically evaluate the created content paired with human playtesting. Participants in four different scenarios are asked about their perception of changes made to the level both before and after balancing, and vice versa. Based on descriptive and statistical analysis, our findings indicate that the PCGRL-based balancing positively influences players’ perceived balance for most scenarios, albeit with differences in aspects of the balancing between scenarios.

We present GenGO(1), a system for exploring papers published in ACL conferences. Paper data stored in our database is enriched with multi-aspect summaries, extracted named entities, a field of study label, and text embeddings by our data processing pipeline. These metadata are used in our web-based user interface to enable researchers to quickly find papers relevant to their interests, and grasp an overview of papers without reading full-text of papers. To keep GenGO available online as long as possible, we design GenGO to be simple and efficient to reduce maintenance and financial costs. In addition, the modularity of our data processing pipeline lets developers easily extend it to add new features. We make our code available to foster open development and transparency: https://gengo.sotaro.io/.(2)

Purpose The purpose of this work is to explore the new possibilities enabled by the recent introduction of RDF-star, an extension that allows for statements about statements within the Resource Description Framework (RDF). Alongside Named Graphs, this approach offers opportunities to leverage a meta-level for data modeling and data applications. Design/methodology/approach In this extended paper, the authors build onto three modeling use cases published in a previous paper: (1) provide provenance information, (2) maintain backwards compatibility for existing models, and (3) reduce the complexity of a data model. The authors present two scenarios where they implement the use of the meta-level to extend a data model with meta-information. Findings The authors present three abstract patterns for actively using the meta-level in data modeling. The authors showcase the implementation of the meta-level through two scenarios from our research project: (1) the authors introduce a workflow for triple annotation that uses the meta-level to enable users to comment on individual statements, such as for reporting errors or adding supplementary information. (2) The authors demonstrate how adding meta-information to a data model can accommodate highly specialized data while maintaining the simplicity of the underlying model. Practical implications Through the formulation of data modeling patterns with RDF-star and the demonstration of their application in two scenarios, the authors advocate for data modelers to embrace the meta-level. Originality/value With RDF-star being a very new extension to RDF, to the best of the authors’ knowledge, they are among the first to relate it to other meta-level approaches and demonstrate its application in real-world scenarios.

Game economy design significantly shapes the player experience and progression speed. Modern game economies are becoming increasingly complex and can be very sensitive to even minor numerical adjustments, which may have an unexpected impact on the overall gaming experience. Consequently, thorough manual testing and fine-tuning during development are essential. Unlike existing works that address algorithmic balancing for specific games or genres, this work adopts a more abstract approach, focusing on game balancing through its economy, detached from a specific game. We propose GEEvo (Game Economy Evolution), a framework to generate graph-based game economies and balancing both, newly generated or existing economies. GEEvo uses a two-step approach where evolutionary algorithms are used to first generate an economy and then balance it based on specified objectives, such as generated resources or damage dealt over time. We define different objectives by differently parameterizing the fitness function using data from multiple simulation runs of the economy. To support this, we define a lightweight and flexible game economy simulation framework. Our method is tested and benchmarked with various balancing objectives on a generated dataset, and we conduct a case study evaluating damage balancing for two fictional economies of two popular game character classes.

Many disciplines, including the broad Field of Information (iField), offer Data Science (DS) programs. There have been significant efforts exploring an individual discipline's identity and unique contributions to the broader DS education landscape. To advance DS education in the iField, the iSchool Data Science Curriculum Committee (iDSCC) was formed and charged with building and recommending a DS education framework for iSchools. This paper reports on the research process and findings of a series of studies to address important questions: What is the iField identity in the multidisciplinary DS education landscape? What is the status of DS education in iField schools? What knowledge and skills should be included in the core curriculum for iField DS education? What are the jobs available for DS graduates from the iField? What are the differences between graduate-level and undergraduate-level DS education? Answers to these questions will not only distinguish an iField approach to DS education but also define critical components of DS curriculum. The results will inform individual DS programs in the iField to develop curriculum to support undergraduate and graduate DS education in their local context.

The number of scientific publications nowadays is rapidly increasing, causing information overload for researchers and making it hard for scholars to keep up to date with current trends and lines of work. Recent work has tried to address this problem by developing methods for automated summarization in the scholarly domain, but concentrated so far only on monolingual settings, primarily English. In this paper, we consequently explore how state-of-the-art neural abstract summarization models based on a multilingual encoder–decoder architecture can be used to enable cross-lingual extreme summaries of scholarly texts. To this end, we compile a new abstractive cross-lingual summarization dataset for the scholarly domain in four different languages, which enables us to train and evaluate models that process English papers and generate summaries in German, Italian, Chinese and Japanese. We present our new X-SCITLDR dataset for multilingual summarization and thoroughly benchmark different models based on a state-of-the-art multilingual pre-trained model, including a two-stage pipeline approach that independently summarizes and translates, as well as a direct cross-lingual model. We additionally explore the benefits of intermediate-stage training using English monolingual summarization and machine translation as intermediate tasks and analyze performance in zero- and few-shot scenarios. Finally, we investigate how to make our approach more efficient on the basis of knowledge distillation methods, which make it possible to shrink the size of our models, so as to reduce the computational complexity of the summarization inference.

The balancing process for game levels in a competitive two-player context involves a lot of manual work and testing, particularly in non-symmetrical game levels. In this paper, we propose an architecture for automated balancing of tile-based levels within the recently introduced PCGRL framework (procedural content generation via reinforcement learning). Our architecture is divided into three parts: (1) a level generator, (2) a balancing agent and, (3) a reward modeling simulation. By playing the level in a simulation repeatedly, the balancing agent is rewarded for modifying it towards the same win rates for all players. To this end, we introduce a novel family of swap-based representations to increase robustness towards playability. We show that this approach is capable to teach an agent how to alter a level for balancing better and faster than plain PCGRL. In addition, by analyzing the agent's swapping behavior, we can draw conclusions about which tile types influence the balancing most. We test and show our results using the Neural MMO (NMMO) environment in a competitive two-player setting.

Nowadays there is a growing trend in many scientific disciplines to support researchers by providing enhanced information access through linking of publications and underlying datasets, so as to support research with infrastructure to enhance reproducibility and reusability of research results. In this research note, we present an overview of an ongoing research project, named VADIS (VAriable Detection, Interlinking and Summarization), that aims at developing technology and infrastructure for enhanced information access in the Social Sciences via search and summarization of publications on the basis of automatic identification and indexing of survey variables in text. We provide an overview of the overarching vision underlying our project, its main components, and related challenges, as well as a thorough discussion of how these are meant to address the limitations of current information access systems for publications in the Social Sciences. We show how this goal can be concretely implemented in an end-user system by presenting a search prototype, which is based on user requirements collected from qualitative interviews with empirical Social Science researchers.

The Resource Description Framework is well-established as a lingua franca for data modeling and is designed to integrate heterogeneous data at instance and schema level using statements. While RDF is conceptually simple, data models nevertheless get complex, when complex data needs to be represented. Additional levels of indirection with intermediate resources instead of simple properties lead to higher barriers for prospective users of the data. Based on three patterns, we argue that shifting information to a meta-level can not only be used to (1) provide provenance information, but can also help to (2) maintain backwards compatibility for existing models, and to (3) reduce the complexity of a data model. There are, however, multiple ways in RDF to use a meta-level, i.e., to provide additional statements about statements. With Named Graphs, there exists a well-established mechanism to describe groups of statements. Since its inception, however, it has been hard to make statements about single statements. With the introduction of RDF-star, a new way to provide data about single statements is now available. We show that the combination of RDF-star and Named Graphs is a viable solution to express data on a meta-level and propose that this meta-level should be used as first class citizen in data modeling.

The number of scientific publications nowadays is rapidly increasing, causing information overload for researchers and making it hard for scholars to keep up to date with current trends and lines of work. Consequently, recent work on applying text mining technologies for scholarly publications has investigated the application of automatic text summarization technologies, including extreme summarization, for this domain. However, previous work has concentrated only on monolingual settings, primarily in English. In this paper, we fill this research gap and present an abstractive cross-lingual summarization dataset for four different languages in the scholarly domain, which enables us to train and evaluate models that process English papers and generate summaries in German, Italian, Chinese and Japanese. We present our new X-SCITLDR dataset for multilingual summarization and thoroughly benchmark different models based on a state-of-the-art multilingual pre-trained model, including a two-stage 'summarize and translate' approach and a direct cross-lingual model. We additionally explore the benefits of intermediate-stage training using English monolingual summarization and machine translation as intermediate tasks and analyze performance in zero- and few-shot scenarios.

Persistent identification of entities plays a major role in the progress of digitization of many fields. In the scholarly publishing realm there are already persistent identifiers (PID) for papers (DOI), people (ORCID), organisation (GRID, ROR), books (ISBN) but there is no generally accepted PID system for scholarly events such as conferences or workshops yet. This article describes the relevant use cases that motivate the introduction of persistent identifiers for conferences. The use cases were mainly derived from interviews, discussions with experts and their previous work. As primary stakeholders who are involved in the typical conference event life cycle researchers, conference organizers, and data consumers were identified. The resulting list of use cases illustrates how PIDs for conference events will improve the current situation for these stakeholders and help with problems they are facing today.

In this paper, we provide an overview of the SV-Ident shared task as part of the 3rd Workshop on Scholarly Document Processing (SDP) at COLING 2022. In the shared task, participants were provided with a sentence and a vocabulary of variables, and asked to identify which variables, if any, are mentioned in individual sentences from scholarly documents in full text. Two teams made a total of 9 submissions to the shared task leaderboard. While none of the teams improve on the baseline systems, we still draw insights from their submissions. Furthermore, we provide a detailed evaluation. Data and baselines for our shared task are freely available at https://github.com/vadis-project/sv-ident