BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Marian-Andrei Rizoiu

Marian-Andrei Rizoiu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Social and Information NetworksMachine LearningArtificial Intelligencecs.CYeess.SPInformation Retrievalecon.GNHuman-Computer Interactionphysics.soc-phq-fin.EC

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
10topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

Published work

12 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