arXiv subjects

Vicenç Gómez

Publications and source records attributed to Vicenç Gómez.

At least 19 recordsLinked to original sources

arXiv2026

Rewarding Engagement and Personalization in Popularity-Based Rankings Amplifies Extremism and Polarization

Despite extensive research, the mechanisms through which online platforms shape extremism and polarization remain poorly understood. We identify and test a mechanism, grounded in empirical evidence, that explains how ranking algorithms can amplify both phenomena. This mechanism is based on well-documented assumptions: (i) users exhibit position bias and tend to prefer items displayed higher in the ranking, (ii) users prefer like-minded content, (iii) users with more extreme views are more likely to engage actively, and (iv) ranking algorithms are popularity-based, assigning higher positions to items that attract more clicks. Under these conditions, when platforms additionally reward active engagement and implement personalized rankings, users are inevitably driven toward more extremist and polarized news consumption. We formalize this mechanism in a dynamical model, which we evaluate by means of simulations and interactive experiments with hundreds of human participants, where the rankings are updated dynamically in response to user activity.

cs.SI↗

arXiv2026

From Next Token Prediction to (STRIPS) World Models

We study whether next-token prediction can yield world models that truly support planning, in a controlled symbolic setting where propositional STRIPS action models are learned from action traces alone and correctness can be evaluated exactly. We introduce two architectures. The first is the STRIPS Transformer, a symbolically aligned model grounded in theoretical results linking transformers and the formal language structure of STRIPS domains. The second is a standard transformer architecture without explicit symbolic structure built in, for which we study different positional encoding schemes and attention aggregation mechanisms. We evaluate both architectures on five classical planning domains, measuring training accuracy, generalization, and planning performance across domains and problem sizes. Interestingly, both approaches can be used to produce models that support planning with off-the-shelf STRIPS planners over exponentially many unseen initial states and goals. Although the STRIPS Transformer incorporates a strong symbolic inductive bias, it is harder to optimize and requires larger datasets to generalize reliably. In contrast, a standard transformer with stick-breaking attention achieves near-perfect training accuracy and strong generalization. Finally, standard transformers without stick-breaking attention do not generalize to long traces, whereas a symbolic STRIPS model extracted from a transformer trained on shorter traces does.

cs.AI↗

arXiv2026

A Decade of News Forum Interactions: Threaded Conversations, Signed Votes, and Topical Tags

We present a large-scale, longitudinal dataset capturing user activity on the online platform of DerStandard, a major Austrian newspaper. The dataset spans ten years (2013-2022) and includes over 75 million user comments, more than 400 million votes, and detailed metadata on articles and user interactions. It provides structured conversation threads, explicit up- and downvotes of user comments and editorial topic labels, enabling rich analyses of online discourse while preserving user privacy. To ensure this privacy, all persistent identifiers are anonymized using salted hash functions, and the raw comment texts are not publicly shared. Instead, we release pre-computed vector representations derived from a state-of-the-art embedding model. The dataset supports research on discussion dynamics, network structures, and semantic analyses in the mid-resourced language German, offering a reusable resource across computational social science and related fields.

cs.SI↗

arXiv2025

A Simple and Explainable Model for Park-and-Ride Car Park Occupancy Prediction

In a scenario of growing usage of park-and-ride facilities, understanding and predicting car park occupancy is becoming increasingly important. This study presents a model that effectively captures the occupancy patterns of park-and-ride car parks for commuters using truncated normal distributions for vehicle arrival and departure times. The objective is to develop a predictive model with minimal parameters corresponding to commuter behaviour, enabling the estimation of parking saturation and unfulfilled demand. The proposed model successfully identifies the regular, periodic nature of commuter parking behaviour, where vehicles arrive in the morning and depart in the afternoon. It operates using aggregate data, eliminating the need for individual tracking of arrivals and departures. The model's predictive and now-casting capabilities are demonstrated through real-world data from car parks in the Barcelona Metropolitan Area. A simple model extension furthermore enables the prediction of when a car park will reach its occupancy limit and estimates the additional spaces required to accommodate such excess demand. Thus, beyond forecasting, the model serves as a valuable tool for evaluating interventions, such as expanding parking capacity, to optimize park-and-ride facilities.

stat.AP↗

arXiv2025

Analyzing News Engagement on Facebook: Tracking Ideological Segregation and News Quality in the Facebook URL Dataset

The Facebook Privacy-Protected Full URLs Dataset was released to enable independent, academic research on the impact of Facebook's platform on society while ensuring user privacy. The dataset has been used in several studies to analyze the relationship between social media engagement and societal issues such as misinformation, polarization, and the quality of consumed news. In this paper, we conduct a comprehensive analysis of the engagement with popular news domains, covering four years from January 2017 to December 2020, with a focus on user engagement metrics related to news URLs in the U.S. By incorporating the ideological alignment and composite score of quality and reliability of news sources, along with users' political preferences, we construct weighted averages of ideology and quality of news consumption for liberal, conservative, and moderate audiences. This allows us to track the evolution of (i) the ideological gap in news consumption between liberals and conservatives and (ii) the average quality of each group's news consumption. We identify two major shifts in trends, each tied to engagement changes. In both, the ideological gap widens and news quality declines. However, engagement rises in the first shift but falls in the second. Finally, we contextualize these trends by linking them to two major Facebook News Feed updates. Our findings provide empirical evidence to better understand user behavior and engagement with news and their leaning and reliability during the period covered by the dataset.

cs.CY↗

arXiv2024

Hierarchical Average-Reward Linearly-solvable Markov Decision Processes

We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike previous work, our approach allows learning low-level and high-level tasks simultaneously, without imposing limiting restrictions on the low-level tasks. Our method relies on partitions of the state space that create smaller subtasks that are easier to solve, and the equivalence between such partitions to learn more efficiently. We then exploit the compositionality of low-level tasks to exactly represent the value function of the high-level task. Experiments show that our approach can outperform flat average-reward reinforcement learning by one or several orders of magnitude.

cs.LG↗

arXiv2024

Planning with a Learned Policy Basis to Optimally Solve Complex Tasks

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward specifications is a challenging problem. We propose to use successor features to learn a policy basis so that each (sub)policy in it solves a well-defined subproblem. In a task described by a finite state automaton (FSA) that involves the same set of subproblems, the combination of these (sub)policies can then be used to generate an optimal solution without additional learning. In contrast to other methods that combine (sub)policies via planning, our method asymptotically attains global optimality, even in stochastic environments.

cs.LG↗

arXiv2024

Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings

We present a novel edge-level ego-network encoding for learning on graphs that can boost Message Passing Graph Neural Networks (MP-GNNs) by providing additional node and edge features or extending message-passing formats. The proposed encoding is sufficient to distinguish Strongly Regular Graphs, a family of challenging 3-WL equivalent graphs. We show theoretically that such encoding is more expressive than node-based sub-graph MP-GNNs. In an empirical evaluation on four benchmarks with 10 graph datasets, our results match or improve previous baselines on expressivity, graph classification, graph regression, and proximity tasks -- while reducing memory usage by 18.1x in certain real-world settings.

cs.LG↗

arXiv2024

Combined Task and Motion Planning Via Sketch Decompositions (Extended Version with Supplementary Material)

The challenge in combined task and motion planning (TAMP) is the effective integration of a search over a combinatorial space, usually carried out by a task planner, and a search over a continuous configuration space, carried out by a motion planner. Using motion planners for testing the feasibility of task plans and filling out the details is not effective because it makes the geometrical constraints play a passive role. This work introduces a new interleaved approach for integrating the two dimensions of TAMP that makes use of sketches, a recent simple but powerful language for expressing the decomposition of problems into subproblems. A sketch has width 1 if it decomposes the problem into subproblems that can be solved greedily in linear time. In the paper, a general sketch is introduced for several classes of TAMP problems which has width 1 under suitable assumptions. While sketch decompositions have been developed for classical planning, they offer two important benefits in the context of TAMP. First, when a task plan is found to be unfeasible due to the geometric constraints, the combinatorial search resumes in a specific sub-problem. Second, the sampling of object configurations is not done once, globally, at the start of the search, but locally, at the start of each subproblem. Optimizations of this basic setting are also considered and experimental results over existing and new pick-and-place benchmarks are reported.

cs.RO↗

arXiv2024

Unpacking polarization: Antagonism and Alignment in Signed Networks of Online Interaction

Political conflict is an essential element of democratic systems, but can also threaten their existence if it becomes too intense. This happens particularly when most political issues become aligned along the same major fault line, splitting society into two antagonistic camps. In the 20th century, major fault lines were formed by structural conflicts, like owners vs workers, center vs periphery, etc. But these classical cleavages have since lost their explanatory power. Instead of theorizing new cleavages, we present the FAULTANA (FAULT-line Alignment Network Analysis) pipeline, a computational method to uncover major fault lines in data of signed online interactions. Our method makes it possible to quantify the degree of antagonism prevalent in different online debates, as well as how aligned each debate is to the major fault line. This makes it possible to identify the wedge issues driving polarization, characterized by both intense antagonism and alignment. We apply our approach to large-scale data sets of Birdwatch, a US-based Twitter fact-checking community and the discussion forums of DerStandard, an Austrian online newspaper. We find that both online communities are divided into two large groups and that their separation follows political identities and topics. In addition, for DerStandard, we pinpoint issues that reinforce societal fault lines and thus drive polarization. We also identify issues that trigger online conflict without strictly aligning with those dividing lines (e.g. COVID-19). Our methods allow us to construct a time-resolved picture of affective polarization that shows the separate contributions of cohesiveness and divisiveness to the dynamics of alignment during contentious elections and events.

cs.SI↗

arXiv2022

Beyond 1-WL with Local Ego-Network Encodings

Identifying similar network structures is key to capture graph isomorphisms and learn representations that exploit structural information encoded in graph data. This work shows that ego-networks can produce a structural encoding scheme for arbitrary graphs with greater expressivity than the Weisfeiler-Lehman (1-WL) test. We introduce IGEL, a preprocessing step to produce features that augment node representations by encoding ego-networks into sparse vectors that enrich Message Passing (MP) Graph Neural Networks (GNNs) beyond 1-WL expressivity. We describe formally the relation between IGEL and 1-WL, and characterize its expressive power and limitations. Experiments show that IGEL matches the empirical expressivity of state-of-the-art methods on isomorphism detection while improving performance on seven GNN architectures.

cs.LG↗

arXiv2022

Crowding out the truth? A simple model of misinformation, polarization and meaningful social interactions

This paper provides a simple theoretical framework to evaluate the effect of key parameters of ranking algorithms, namely popularity and personalization parameters, on measures of platform engagement, misinformation and polarization. The results show that an increase in the weight assigned to online social interactions (e.g., likes and shares) and to personalized content may increase engagement on the social media platform, while at the same time increasing misinformation and/or polarization. By exploiting Facebook's 2018 "Meaningful Social Interactions" algorithmic ranking update, we also provide direct empirical support for some of the main predictions of the model.

cs.SI↗

arXiv2022

Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes

In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the partitions. We represent value functions on several levels of abstraction, and use the compositionality of subtasks to estimate the optimal values of the states in each partition. The policy is implicitly defined on these optimal value estimates, rather than being decomposed among the subtasks. As a consequence, our approach can learn the globally optimal policy, and does not suffer from the non-stationarity of high-level decisions. If several partitions have equivalent dynamics, the subtasks of those partitions can be shared. If the set of boundary states is smaller than the entire state space, our approach can have significantly smaller sample complexity than that of a flat learner, and we validate this empirically in several experiments.

cs.LG↗

arXiv2021

Uncovering the Limits of Text-based Emotion Detection

Identifying emotions from text is crucial for a variety of real world tasks. We consider the two largest now-available corpora for emotion classification: GoEmotions, with 58k messages labelled by readers, and Vent, with 33M writer-labelled messages. We design a benchmark and evaluate several feature spaces and learning algorithms, including two simple yet novel models on top of BERT that outperform previous strong baselines on GoEmotions. Through an experiment with human participants, we also analyze the differences between how writers express emotions and how readers perceive them. Our results suggest that emotions expressed by writers are harder to identify than emotions that readers perceive. We share a public web interface for researchers to explore our models.

cs.CL↗

arXiv2021

Deep Policies for Width-Based Planning in Pixel Domains

Width-based planning has demonstrated great success in recent years due to its ability to scale independently of the size of the state space. For example, Bandres et al. (2018) introduced a rollout version of the Iterated Width algorithm whose performance compares well with humans and learning methods in the pixel setting of the Atari games suite. In this setting, planning is done on-line using the "screen" states and selecting actions by looking ahead into the future. However, this algorithm is purely exploratory and does not leverage past reward information. Furthermore, it requires the state to be factored into features that need to be pre-defined for the particular task, e.g., the B-PROST pixel features. In this work, we extend width-based planning by incorporating an explicit policy in the action selection mechanism. Our method, called $π$-IW, interleaves width-based planning and policy learning using the state-actions visited by the planner. The policy estimate takes the form of a neural network and is in turn used to guide the planning step, thus reinforcing promising paths. Surprisingly, we observe that the representation learned by the neural network can be used as a feature space for the width-based planner without degrading its performance, thus removing the requirement of pre-defined features for the planner. We compare $π$-IW with previous width-based methods and with AlphaZero, a method that also interleaves planning and learning, in simple environments, and show that $π$-IW has superior performance. We also show that $π$-IW algorithm outperforms previous width-based methods in the pixel setting of Atari games suite.

cs.AI↗

arXiv2021

Hierarchical Width-Based Planning and Learning

Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari games. These methods scale independently of the size of the state-space, but exponentially in the problem width. In practice, running the algorithm with a width larger than 1 is computationally intractable, prohibiting IW from solving higher width problems. In this paper, we present a hierarchical algorithm that plans at two levels of abstraction. A high-level planner uses abstract features that are incrementally discovered from low-level pruning decisions. We illustrate this algorithm in classical planning PDDL domains as well as in pixel-based simulator domains. In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2. For pixel-based domains, we show how in combination with a learned policy and a learned value function, the proposed hierarchical IW can outperform current flat IW-based planners in Atari games with sparse rewards.

cs.AI↗

arXiv2020

Inductive Graph Embeddings through Locality Encodings

Learning embeddings from large-scale networks is an open challenge. Despite the overwhelming number of existing methods, is is unclear how to exploit network structure in a way that generalizes easily to unseen nodes, edges or graphs. In this work, we look at the problem of finding inductive network embeddings in large networks without domain-dependent node/edge attributes. We propose to use a set of basic predefined local encodings as the basis of a learning algorithm. In particular, we consider the degree frequencies at different distances from a node, which can be computed efficiently for relatively short distances and a large number of nodes. Interestingly, the resulting embeddings generalize well across unseen or distant regions in the network, both in unsupervised settings, when combined with language model learning, as well as in supervised tasks, when used as additional features in a neural network. Despite its simplicity, this method achieves state-of-the-art performance in tasks such as role detection, link prediction and node classification, and represents an inductive network embedding method directly applicable to large unattributed networks.

cs.LG↗

arXiv2020

Adaptive Smoothing Path Integral Control

In Path Integral control problems a representation of an optimally controlled dynamical system can be formally computed and serve as a guidepost to learn a parametrized policy. The Path Integral Cross-Entropy (PICE) method tries to exploit this, but is hampered by poor sample efficiency. We propose a model-free algorithm called ASPIC (Adaptive Smoothing of Path Integral Control) that applies an inf-convolution to the cost function to speedup convergence of policy optimization. We identify PICE as the infinite smoothing limit of such technique and show that the sample efficiency problems that PICE suffers disappear for finite levels of smoothing. For zero smoothing this method becomes a greedy optimization of the cost, which is the standard approach in current reinforcement learning. We show analytically and empirically that intermediate levels of smoothing are optimal, which renders the new method superior to both PICE and direct cost-optimization.

eess.SY↗