BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Marian-Andrei Rizoiu

Marian-Andrei Rizoiu appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Social and Information NetworksMachine LearningArtificial IntelligenceInformation Retrievalcs.CYData Structures and Algorithmseess.SPphysics.soc-phComputation and LanguageComputer VisionDatabasesecon.GNHuman-Computer Interactionq-fin.EC

Catalog footprint

What is connected

20works
14topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

20 published item(s)

preprint2026arXiv

UTS at PsyDefDetect: Multi-Agent Councils and Absence-Based Reasoning for Defense Mechanism Classification

This paper describes our system for classifying psychological defense mechanisms in emotional support dialogues using the Defense Mechanism Rating Scales (DMRS), placing second (F1 0.406) among 64 teams. A central insight is that defense mechanisms are defined by what is absent: missing affect, blocked cognition, denied reality. We encode this as an affect-cognition integration spectrum in prompt-level clinical rules, which account for the largest single gain (+11.4pp F1). Our architecture is a multi-phase deliberative council of Gemini 2.5 agents where class-specific advocates rate evidence strength rather than voting, achieving F1 0.382 with no fine-tuning - a top-5 result on its own. We find, however, that the council is confidently wrong about minority classes: 59-80% of stable minority predictions are incorrect, driven by a systematic "L7 attractor" in which emotional content defaults to the majority class. A targeted override ensemble from three fine-tuned Qwen3.5 models applies 16 overrides (+2.4pp), selected by a structured multi-agent system (builder, critic, regression guard) that produced a larger F1 gain in one iteration than 8 prior attempts combined.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Efficient Non-parametric Bayesian Hawkes Processes

In this paper, we develop an efficient nonparametric Bayesian estimation of the kernel function of Hawkes processes. The non-parametric Bayesian approach is important because it provides flexible Hawkes kernels and quantifies their uncertainty. Our method is based on the cluster representation of Hawkes processes. Utilizing the finite support assumption of the Hawkes process, we efficiently sample random branching structures and thus, we split the Hawkes process into clusters of Poisson processes. We derive two algorithms -- a block Gibbs sampler and a maximum a posteriori estimator based on expectation maximization -- and we show that our methods have a linear time complexity, both theoretically and empirically. On synthetic data, we show our methods to be able to infer flexible Hawkes triggering kernels. On two large-scale Twitter diffusion datasets, we show that our methods outperform the current state-of-the-art in goodness-of-fit and that the time complexity is linear in the size of the dataset. We also observe that on diffusions related to online videos, the learned kernels reflect the perceived longevity for different content types such as music or pets videos.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Slipping to the Extreme: A Mixed Method to Explain How Extreme Opinions Infiltrate Online Discussions

Qualitative research provides methodological guidelines for observing and studying communities and cultures on online social media platforms. However, such methods demand considerable manual effort from researchers and can be overly focused and narrowed to certain online groups. This work proposes a complete solution to accelerate the qualitative analysis of problematic online speech, focusing on opinions emerging from online communities by leveraging machine learning algorithms. First, we employ qualitative methods of deep observation for understanding problematic online speech. This initial qualitative study constructs an ontology of problematic speech, which contains social media postings annotated with their underlying opinions. The qualitative study dynamically constructs the set of opinions, simultaneous with labeling the postings. Next, we use keywords to collect a large dataset from three online social media platforms (Facebook, Twitter, and Youtube). Finally, we introduce an iterative data exploration procedure to augment the dataset. It alternates between a data sampler -- which balances exploration and exploitation of unlabeled data -- the automatic labeling of the sampled data, the manual inspection by the qualitative mapping team, and, finally, the retraining of the automatic opinion classifiers. We present both qualitative and quantitative results. First, we show that our human-in-the-loop method successfully augments the initial qualitatively labeled and narrowly focused dataset and constructs a more encompassing dataset. Next, we present detailed case studies of the dynamics of problematic speech in a far-right Facebook group, exemplifying its mutation from conservative to extreme. Finally, we examine the dynamics of opinion emergence and co-occurrence, and we hint at some pathways through which extreme opinions creep into the mainstream online discourse.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Describing and Predicting Online Items with Reshare Cascades via Dual Mixture Self-exciting Processes

It is well-known that online behavior is long-tailed, with most cascaded actions being short and a few being very long. A prominent drawback in generative models for online events is the inability to describe unpopular items well. This work addresses these shortcomings by proposing dual mixture self-exciting processes to jointly learn from groups of cascades. We first start from the observation that maximum likelihood estimates for content virality and influence decay are separable in a Hawkes process. Next, our proposed model, which leverages a Borel mixture model and a kernel mixture model, jointly models the unfolding of a heterogeneous set of cascades. When applied to cascades of the same online items, the model directly characterizes their spread dynamics and supplies interpretable quantities, such as content virality and content influence decay, as well as methods for predicting the final content popularities. On two retweet cascade datasets -- one relating to YouTube videos and the second relating to controversial news articles -- we show that our models capture the differences between online items at the granularity of items, publishers and categories. In particular, we are able to distinguish between far-right, conspiracy, controversial and reputable online news articles based on how they diffuse through social media, achieving an F1 score of 0.945. On holdout datasets, we show that the dual mixture model provides, for reshare diffusion cascades especially unpopular ones, better generalization performance and, for online items, accurate item popularity predictions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Estimating Attention Flow in Online Video Networks

Online videos have shown tremendous increase in Internet traffic. Most video hosting sites implement recommender systems, which connect the videos into a directed network and conceptually act as a source of pathways for users to navigate. At present, little is known about how human attention is allocated over such large-scale networks, and about the impacts of the recommender systems. In this paper, we first construct the Vevo network -- a YouTube video network with 60,740 music videos interconnected by the recommendation links, and we collect their associated viewing dynamics. This results in a total of 310 million views every day over a period of 9 weeks. Next, we present large-scale measurements that connect the structure of the recommendation network and the video attention dynamics. We use the bow-tie structure to characterize the Vevo network and we find that its core component (23.1% of the videos), which occupies most of the attention (82.6% of the views), is made out of videos that are mainly recommended among themselves. This is indicative of the links between video recommendation and the inequality of attention allocation. Finally, we address the task of estimating the attention flow in the video recommendation network. We propose a model that accounts for the network effects for predicting video popularity, and we show it consistently outperforms the baselines. This model also identifies a group of artists gaining attention because of the recommendation network. Altogether, our observations and our models provide a new set of tools to better understand the impacts of recommender systems on collective social attention.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Graph modelling approaches for motorway traffic flow prediction

Traffic flow prediction, particularly in areas that experience highly dynamic flows such as motorways, is a major issue faced in traffic management. Due to increasingly large volumes of data sets being generated every minute, deep learning methods have been used extensively in the latest years for both short and long term prediction. However, such models, despite their efficiency, need large amounts of historical information to be provided, and they take a considerable amount of time and computing resources to train, validate and test. This paper presents two new spatial-temporal approaches for building accurate short-term prediction along a popular motorway in Sydney, by making use of the graph structure of the motorway network (including exits and entries). The methods are built on proximity-based approaches, denoted backtracking and interpolation, which uses the most recent and closest traffic flow information for each of the target counting stations along the motorway. The results indicate that for short-term predictions (less than 10 minutes into the future), the proposed graph-based approaches outperform state-of-the-art deep learning models, such as long-term short memory, convolutional neuronal networks or hybrid models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Modeling Information Cascades with Self-exciting Processes via Generalized Epidemic Models

Epidemic models and self-exciting processes are two types of models used to describe diffusion phenomena online and offline. These models were originally developed in different scientific communities, and their commonalities are under-explored. This work establishes, for the first time, a general connection between the two model classes via three new mathematical components. The first is a generalized version of stochastic Susceptible-Infected-Recovered (SIR) model with arbitrary recovery time distributions; the second is the relationship between the (latent and arbitrary) recovery time distribution, recovery hazard function, and the infection kernel of self-exciting processes; the third includes methods for simulating, fitting, evaluating and predicting the generalized process. On three large Twitter diffusion datasets, we conduct goodness-of-fit tests and holdout log-likelihood evaluation of self-exciting processes with three infection kernels --- exponential, power-law and Tsallis Q-exponential. We show that the modeling performance of the infection kernels varies with respect to the temporal structures of diffusions, and also with respect to user behavior, such as the likelihood of being bots. We further improve the prediction of popularity by combining two models that are identified as complementary by the goodness-of-fit tests.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Predicting Skill Shortages in Labor Markets: A Machine Learning Approach

Skill shortages are a drain on society. They hamper economic opportunities for individuals, slow growth for firms, and impede labor productivity in aggregate. Therefore, the ability to understand and predict skill shortages in advance is critical for policy-makers and educators to help alleviate their adverse effects. This research implements a high-performing Machine Learning approach to predict occupational skill shortages. In addition, we demonstrate methods to analyze the underlying skill demands of occupations in shortage and the most important features for predicting skill shortages. For this work, we compile a unique dataset of both Labor Demand and Labor Supply occupational data in Australia from 2012 to 2018. This includes data from 7.7 million job advertisements (ads) and 20 official labor force measures. We use these data as explanatory variables and leverage the XGBoost classifier to predict yearly skills shortage classifications for 132 standardized occupations. The models we construct achieve macro-F1 average performance scores of up to 83 per cent. Our results show that job ads data and employment statistics were the highest performing feature sets for predicting year-to-year skills shortage changes for occupations. We also find that features such as 'Hours Worked', years of 'Education', years of 'Experience', and median 'Salary' are highly important features for predicting occupational skill shortages. This research provides a robust data-driven approach for predicting and analyzing skill shortages, which can assist policy-makers, educators, and businesses to prepare for the future of work.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Traffic congestion anomaly detection and prediction using deep learning

Congestion prediction represents a major priority for traffic management centres around the world to ensure timely incident response handling. The increasing amounts of generated traffic data have been used to train machine learning predictors for traffic, however, this is a challenging task due to inter-dependencies of traffic flow both in time and space. Recently, deep learning techniques have shown significant prediction improvements over traditional models, however, open questions remain around their applicability, accuracy and parameter tuning. This paper brings two contributions in terms of: 1) applying an outlier detection an anomaly adjustment method based on incoming and historical data streams, and 2) proposing an advanced deep learning framework for simultaneously predicting the traffic flow, speed and occupancy on a large number of monitoring stations along a highly circulated motorway in Sydney, Australia, including exit and entry loop count stations, and over varying training and prediction time horizons. The spatial and temporal features extracted from the 36.34 million data points are used in various deep learning architectures that exploit their spatial structure (convolutional neuronal networks), their temporal dynamics (recurrent neuronal networks), or both through a hybrid spatio-temporal modelling (CNN-LSTM). We show that our deep learning models consistently outperform traditional methods, and we conduct a comparative analysis of the optimal time horizon of historical data required to predict traffic flow at different time points in the future. Lastly, we prove that the anomaly adjustment method brings significant improvements to using deep learning in both time and space.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Variation across Scales: Measurement Fidelity under Twitter Data Sampling

A comprehensive understanding of data quality is the cornerstone of measurement studies in social media research. This paper presents in-depth measurements on the effects of Twitter data sampling across different timescales and different subjects (entities, networks, and cascades). By constructing complete tweet streams, we show that Twitter rate limit message is an accurate indicator for the volume of missing tweets. Sampling also differs significantly across timescales. While the hourly sampling rate is influenced by the diurnal rhythm in different time zones, the millisecond level sampling is heavily affected by the implementation choices. For Twitter entities such as users, we find the Bernoulli process with a uniform rate approximates the empirical distributions well. It also allows us to estimate the true ranking with the observed sample data. For networks on Twitter, their structures are altered significantly and some components are more likely to be preserved. For retweet cascades, we observe changes in distributions of tweet inter-arrival time and user influence, which will affect models that rely on these features. This work calls attention to noises and potential biases in social data, and provides a few tools to measure Twitter sampling effects.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Adaptively selecting occupations to detect skill shortages from online job ads

Labour demand and skill shortages have historically been difficult to assess given the high costs of conducting representative surveys and the inherent delays of these indicators. This is particularly consequential for fast developing skills and occupations, such as those relating to Data Science and Analytics (DSA). This paper develops a data-driven solution to detecting skill shortages from online job advertisements (ads) data. We first propose a method to generate sets of highly similar skills based on a set of seed skills from job ads. This provides researchers with a novel method to adaptively select occupations based on granular skills data. Next, we apply this adaptive skills similarity technique to a dataset of over 6.7 million Australian job ads in order to identify occupations with the highest proportions of DSA skills. This uncovers 306,577 DSA job ads across 23 occupational classes from 2012-2019. Finally, we propose five variables for detecting skill shortages from online job ads: (1) posting frequency; (2) salary levels; (3) education requirements; (4) experience demands; and (5) job ad posting predictability. This contributes further evidence to the goal of detecting skills shortages in real-time. In conducting this analysis, we also find strong evidence of skills shortages in Australia for highly technical DSA skills and occupations. These results provide insights to Data Science researchers, educators, and policy-makers from other advanced economies about the types of skills that should be cultivated to meet growing DSA labour demands in the future.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Variational Inference for Sparse Gaussian Process Modulated Hawkes Process

The Hawkes process (HP) has been widely applied to modeling self-exciting events including neuron spikes, earthquakes and tweets. To avoid designing parametric triggering kernel and to be able to quantify the prediction confidence, the non-parametric Bayesian HP has been proposed. However, the inference of such models suffers from unscalability or slow convergence. In this paper, we aim to solve both problems. Specifically, first, we propose a new non-parametric Bayesian HP in which the triggering kernel is modeled as a squared sparse Gaussian process. Then, we propose a novel variational inference schema for model optimization. We employ the branching structure of the HP so that maximization of evidence lower bound (ELBO) is tractable by the expectation-maximization algorithm. We propose a tighter ELBO which improves the fitting performance. Further, we accelerate the novel variational inference schema to linear time complexity by leveraging the stationarity of the triggering kernel. Different from prior acceleration methods, ours enjoys higher efficiency. Finally, we exploit synthetic data and two large social media datasets to evaluate our method. We show that our approach outperforms state-of-the-art non-parametric frequentist and Bayesian methods. We validate the efficiency of our accelerated variational inference schema and practical utility of our tighter ELBO for model selection. We observe that the tighter ELBO exceeds the common one in model selection.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Feature Driven and Point Process Approaches for Popularity Prediction

Predicting popularity, or the total volume of information outbreaks, is an important subproblem for understanding collective behavior in networks. Each of the two main types of recent approaches to the problem, feature-driven and generative models, have desired qualities and clear limitations. This paper bridges the gap between these solutions with a new hybrid approach and a new performance benchmark. We model each social cascade with a marked Hawkes self-exciting point process, and estimate the content virality, memory decay, and user influence. We then learn a predictive layer for popularity prediction using a collection of cascade history. To our surprise, Hawkes process with a predictive overlay outperform recent feature-driven and generative approaches on existing tweet data [43] and a new public benchmark on news tweets. We also found that a basic set of user features and event time summary statistics performs competitively in both classification and regression tasks, and that adding point process information to the feature set further improves predictions. From these observations, we argue that future work on popularity prediction should compare across feature-driven and generative modeling approaches in both classification and regression tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

How to Use Temporal-Driven Constrained Clustering to Detect Typical Evolutions

In this paper, we propose a new time-aware dissimilarity measure that takes into account the temporal dimension. Observations that are close in the description space, but distant in time are considered as dissimilar. We also propose a method to enforce the segmentation contiguity, by introducing, in the objective function, a penalty term inspired from the Normal Distribution Function. We combine the two propositions into a novel time-driven constrained clustering algorithm, called TDCK-Means, which creates a partition of coherent clusters, both in the multidimensional space and in the temporal space. This algorithm uses soft semi-supervised constraints, to encourage adjacent observations belonging to the same entity to be assigned to the same cluster. We apply our algorithm to a Political Studies dataset in order to detect typical evolution phases. We adapt the Shannon entropy in order to measure the entity contiguity, and we show that our proposition consistently improves temporal cohesion of clusters, without any significant loss in the multidimensional variance.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Temporal Multinomial Mixture for Instance-Oriented Evolutionary Clustering

Evolutionary clustering aims at capturing the temporal evolution of clusters. This issue is particularly important in the context of social media data that are naturally temporally driven. In this paper, we propose a new probabilistic model-based evolutionary clustering technique. The Temporal Multinomial Mixture (TMM) is an extension of classical mixture model that optimizes feature co-occurrences in the trade-off with temporal smoothness. Our model is evaluated for two recent case studies on opinion aggregation over time. We compare four different probabilistic clustering models and we show the superiority of our proposal in the task of instance-oriented clustering.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

ClusPath: A Temporal-driven Clustering to Infer Typical Evolution Paths

We propose ClusPath, a novel algorithm for detecting general evolution tendencies in a population of entities. We show how abstract notions, such as the Swedish socio-economical model (in a political dataset) or the companies fiscal optimization (in an economical dataset) can be inferred from low-level descriptive features. Such high-level regularities in the evolution of entities are detected by combining spatial and temporal features into a spatio-temporal dissimilarity measure and using semi-supervised clustering techniques. The relations between the evolution phases are modeled using a graph structure, inferred simultaneously with the partition, by using a "slow changing world" assumption. The idea is to ensure a smooth passage for entities along their evolution paths, which catches the long-term trends in the dataset. Additionally, we also provide a method, based on an evolutionary algorithm, to tune the parameters of ClusPath to new, unseen datasets. This method assesses the fitness of a solution using four opposed quality measures and proposes a balanced compromise.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

CommentWatcher: An Open Source Web-based platform for analyzing discussions on web forums

We present CommentWatcher, an open source tool aimed at analyzing discussions on web forums. Constructed as a web platform, CommentWatcher features automatic mass fetching of user posts from forum on multiple sites, extracting topics, visualizing the topics as an expression cloud and exploring their temporal evolution. The underlying social network of users is simultaneously constructed using the citation relations between users and visualized as a graph structure. Our platform addresses the issues of the diversity and dynamics of structures of webpages hosting the forums by implementing a parser architecture that is independent of the HTML structure of webpages. This allows easy on-the-fly adding of new websites. Two types of users are targeted: end users who seek to study the discussed topics and their temporal evolution, and researchers in need of establishing a forum benchmark dataset and comparing the performances of analysis tools.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Evolution of Privacy Loss in Wikipedia

The cumulative effect of collective online participation has an important and adverse impact on individual privacy. As an online system evolves over time, new digital traces of individual behavior may uncover previously hidden statistical links between an individual's past actions and her private traits. To quantify this effect, we analyze the evolution of individual privacy loss by studying the edit history of Wikipedia over 13 years, including more than 117,523 different users performing 188,805,088 edits. We trace each Wikipedia's contributor using apparently harmless features, such as the number of edits performed on predefined broad categories in a given time period (e.g. Mathematics, Culture or Nature). We show that even at this unspecific level of behavior description, it is possible to use off-the-shelf machine learning algorithms to uncover usually undisclosed personal traits, such as gender, religion or education. We provide empirical evidence that the prediction accuracy for almost all private traits consistently improves over time. Surprisingly, the prediction performance for users who stopped editing after a given time still improves. The activities performed by new users seem to have contributed more to this effect than additional activities from existing (but still active) users. Insights from this work should help users, system designers, and policy makers understand and make long-term design choices in online content creation systems.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Semantic-enriched Visual Vocabulary Construction in a Weakly Supervised Context

One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the semantics of the images. In this paper, we tackle this difficulty by enriching the semantic content of the image representation by using external knowledge. The underlying hypothesis of our work is that creating a more semantically rich representation for images would yield higher machine learning performances, without the need to modify the learning algorithms themselves. The external semantic information is presented under the form of non-positional image labels, therefore positioning our work in a weakly supervised context. Two approaches are proposed: the first one leverages the labels into the visual vocabulary construction algorithm, the result being dedicated visual vocabularies. The second approach adds a filtering phase as a pre-processing of the vocabulary construction. Known positive and known negative sets are constructed and features that are unlikely to be associated with the objects denoted by the labels are filtered. We apply our proposition to the task of content-based image classification and we show that semantically enriching the image representation yields higher classification performances than the baseline representation.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Unsupervised Feature Construction for Improving Data Representation and Semantics

Feature-based format is the main data representation format used by machine learning algorithms. When the features do not properly describe the initial data, performance starts to degrade. Some algorithms address this problem by internally changing the representation space, but the newly-constructed features are rarely comprehensible. We seek to construct, in an unsupervised way, new features that are more appropriate for describing a given dataset and, at the same time, comprehensible for a human user. We propose two algorithms that construct the new features as conjunctions of the initial primitive features or their negations. The generated feature sets have reduced correlations between features and succeed in catching some of the hidden relations between individuals in a dataset. For example, a feature like $sky \wedge \neg building \wedge panorama$ would be true for non-urban images and is more informative than simple features expressing the presence or the absence of an object. The notion of Pareto optimality is used to evaluate feature sets and to obtain a balance between total correlation and the complexity of the resulted feature set. Statistical hypothesis testing is used in order to automatically determine the values of the parameters used for constructing a data-dependent feature set. We experimentally show that our approaches achieve the construction of informative feature sets for multiple datasets.

0 citations0 reviewsNo code linkedOpen access