Pedro Saleiro

Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus et al. · cmu

Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates three popular explainable ML methods in a setting consistent with the intended deployment context. We build on a previous study on e-commerce fraud detection and make crucial modifications to its setup relaxing the simplifying assumptions made in the original work that departed from the deployment context. In doing so, we draw drastically different conclusions from the earlier work and find no evidence for the incremental utility of the tested methods in the task. Our results highlight how seemingly trivial experimental design choices can yield misleading conclusions, with lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended deployment contexts but also developing methods tailored to specific applications. In addition, we believe the design of this experiment can serve as a template for future study designs evaluating explainable ML methods in other real-world contexts.

Diogo Leitão, Pedro Saleiro, Mário A. T. Figueiredo et al.

Human-AI collaboration (HAIC) in decision-making aims to create synergistic teaming between human decision-makers and AI systems. Learning to defer (L2D) has been presented as a promising framework to determine who among humans and AI should make which decisions in order to optimize the performance and fairness of the combined system. Nevertheless, L2D entails several often unfeasible requirements, such as the availability of predictions from humans for every instance or ground-truth labels that are independent from said humans. Furthermore, neither L2D nor alternative approaches tackle fundamental issues of deploying HAIC systems in real-world settings, such as capacity management or dealing with dynamic environments. In this paper, we aim to identify and review these and other limitations, pointing to where opportunities for future research in HAIC may lie.

José Pombal, André F. Cruz, João Bravo et al.

In recent years, machine learning algorithms have become ubiquitous in a multitude of high-stakes decision-making applications. The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within. A biased model can then make decisions that disproportionately harm certain groups in society -- limiting their access to financial services, for example. The awareness of this problem has given rise to the field of Fair ML, which focuses on studying, measuring, and mitigating unfairness in algorithmic prediction, with respect to a set of protected groups (e.g., race or gender). However, the underlying causes for algorithmic unfairness still remain elusive, with researchers divided between blaming either the ML algorithms or the data they are trained on. In this work, we maintain that algorithmic unfairness stems from interactions between models and biases in the data, rather than from isolated contributions of either of them. To this end, we propose a taxonomy to characterize data bias and we study a set of hypotheses regarding the fairness-accuracy trade-offs that fairness-blind ML algorithms exhibit under different data bias settings. On our real-world account-opening fraud use case, we find that each setting entails specific trade-offs, affecting fairness in expected value and variance -- the latter often going unnoticed. Moreover, we show how algorithms compare differently in terms of accuracy and fairness, depending on the biases affecting the data. Finally, we note that under specific data bias conditions, simple pre-processing interventions can successfully balance group-wise error rates, while the same techniques fail in more complex settings.

Ada Martin, Valerie Chen, Sérgio Jesus et al. · cmu

When conducting user studies to ascertain the usefulness of model explanations in aiding human decision-making, it is important to use real-world use cases, data, and users. However, this process can be resource-intensive, allowing only a limited number of explanation methods to be evaluated. Simulated user evaluations (SimEvals), which use machine learning models as a proxy for human users, have been proposed as an intermediate step to select promising explanation methods. In this work, we conduct the first SimEvals on a real-world use case to evaluate whether explanations can better support ML-assisted decision-making in e-commerce fraud detection. We study whether SimEvals can corroborate findings from a user study conducted in this fraud detection context. In particular, we find that SimEvals suggest that all considered explainers are equally performant, and none beat a baseline without explanations -- this matches the conclusions of the original user study. Such correspondences between our results and the original user study provide initial evidence in favor of using SimEvals before running user studies. We also explore the use of SimEvals as a cheap proxy to explore an alternative user study set-up. We hope that this work motivates further study of when and how SimEvals should be used to aid in the design of real-world evaluations.

Sérgio Jesus, José Pombal, Duarte Alves et al.

Evaluating new techniques on realistic datasets plays a crucial role in the development of ML research and its broader adoption by practitioners. In recent years, there has been a significant increase of publicly available unstructured data resources for computer vision and NLP tasks. However, tabular data -- which is prevalent in many high-stakes domains -- has been lagging behind. To bridge this gap, we present Bank Account Fraud (BAF), the first publicly available privacy-preserving, large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabular data generation techniques on an anonymized,real-world bank account opening fraud detection dataset. This setting carries a set of challenges that are commonplace in real-world applications, including temporal dynamics and significant class imbalance. Additionally, to allow practitioners to stress test both performance and fairness of ML methods, each dataset variant of BAF contains specific types of data bias. With this resource, we aim to provide the research community with a more realistic, complete, and robust test bed to evaluate novel and existing methods.

José Pombal, Pedro Saleiro, Mário A. T. Figueiredo et al.

The unparalleled ability of machine learning algorithms to learn patterns from data also enables them to incorporate biases embedded within. A biased model can then make decisions that disproportionately harm certain groups in society. Much work has been devoted to measuring unfairness in static ML environments, but not in dynamic, performative prediction ones, in which most real-world use cases operate. In the latter, the predictive model itself plays a pivotal role in shaping the distribution of the data. However, little attention has been heeded to relating unfairness to these interactions. Thus, to further the understanding of unfairness in these settings, we propose a taxonomy to characterize bias in the data, and study cases where it is shaped by model behaviour. Using a real-world account opening fraud detection case study as an example, we study the dangers to both performance and fairness of two typical biases in performative prediction: distribution shifts, and the problem of selective labels.

José Pombal, Pedro Saleiro, Mário A. T. Figueiredo et al.

Data valuation is a ML field that studies the value of training instances towards a given predictive task. Although data bias is one of the main sources of downstream model unfairness, previous work in data valuation does not consider how training instances may influence both performance and fairness of ML models. Thus, we propose Fairness-Aware Data vauatiOn (FADO), a data valuation framework that can be used to incorporate fairness concerns into a series of ML-related tasks (e.g., data pre-processing, exploratory data analysis, active learning). We propose an entropy-based data valuation metric suited to address our two-pronged goal of maximizing both performance and fairness, which is more computationally efficient than existing metrics. We then show how FADO can be applied as the basis for unfairness mitigation pre-processing techniques. Our methods achieve promising results -- up to a 40 p.p. improvement in fairness at a less than 1 p.p. loss in performance compared to a baseline -- and promote fairness in a data-centric way, where a deeper understanding of data quality takes center stage.

Mário Cardoso, Pedro Saleiro, Pedro Bizarro

Anti-money laundering (AML) regulations mandate financial institutions to deploy AML systems based on a set of rules that, when triggered, form the basis of a suspicious alert to be assessed by human analysts. Reviewing these cases is a cumbersome and complex task that requires analysts to navigate a large network of financial interactions to validate suspicious movements. Furthermore, these systems have very high false positive rates (estimated to be over 95\%). The scarcity of labels hinders the use of alternative systems based on supervised learning, reducing their applicability in real-world applications. In this work we present LaundroGraph, a novel self-supervised graph representation learning approach to encode banking customers and financial transactions into meaningful representations. These representations are used to provide insights to assist the AML reviewing process, such as identifying anomalous movements for a given customer. LaundroGraph represents the underlying network of financial interactions as a customer-transaction bipartite graph and trains a graph neural network on a fully self-supervised link prediction task. We empirically demonstrate that our approach outperforms other strong baselines on self-supervised link prediction using a real-world dataset, improving the best non-graph baseline by $12$ p.p. of AUC. The goal is to increase the efficiency of the reviewing process by supplying these AI-powered insights to the analysts upon review. To the best of our knowledge, this is the first fully self-supervised system within the context of AML detection.

André F Cruz, Catarina Belém, Sérgio Jesus et al.

Tabular data is prevalent in many high-stakes domains, such as financial services or public policy. Gradient Boosted Decision Trees (GBDT) are popular in these settings due to their scalability, performance, and low training cost. While fairness in these domains is a foremost concern, existing in-processing Fair ML methods are either incompatible with GBDT, or incur in significant performance losses while taking considerably longer to train. We present FairGBM, a dual ascent learning framework for training GBDT under fairness constraints, with little to no impact on predictive performance when compared to unconstrained GBDT. Since observational fairness metrics are non-differentiable, we propose smooth convex error rate proxies for common fairness criteria, enabling gradient-based optimization using a ``proxy-Lagrangian'' formulation. Our implementation shows an order of magnitude speedup in training time relative to related work, a pivotal aspect to foster the widespread adoption of FairGBM by real-world practitioners.

João Bento Sousa, Ricardo Moreira, Vladimir Balayan et al.

Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop. Previous work has focused on providing concepts for specific models (eg, neural networks) or data types (eg, images), and by either trying to extract concepts from an already trained network or training self-explainable models through multi-task learning. In this work, we propose ConceptDistil, a method to bring concept explanations to any black-box classifier using knowledge distillation. ConceptDistil is decomposed into two components:(1) a concept model that predicts which domain concepts are present in a given instance, and (2) a distillation model that tries to mimic the predictions of a black-box model using the concept model predictions. We validate ConceptDistil in a real world use-case, showing that it is able to optimize both tasks, bringing concept-explainability to any black-box model.

Jean V. Alves, Diogo Leitão, Sérgio Jesus et al.

Learning to defer (L2D) aims to improve human-AI collaboration systems by learning how to defer decisions to humans when they are more likely to be correct than an ML classifier. Existing research in L2D overlooks key real-world aspects that impede its practical adoption, namely: i) neglecting cost-sensitive scenarios, where type I and type II errors have different costs; ii) requiring concurrent human predictions for every instance of the training dataset; and iii) not dealing with human work-capacity constraints. To address these issues, we propose the \textit{deferral under cost and capacity constraints framework} (DeCCaF). DeCCaF is a novel L2D approach, employing supervised learning to model the probability of human error under less restrictive data requirements (only one expert prediction per instance) and using constraint programming to globally minimize the error cost, subject to workload limitations. We test DeCCaF in a series of cost-sensitive fraud detection scenarios with different teams of 9 synthetic fraud analysts, with individual work-capacity constraints. The results demonstrate that our approach performs significantly better than the baselines in a wide array of scenarios, achieving an average $8.4\%$ reduction in the misclassification cost. The code used for the experiments is available at https://github.com/feedzai/deccaf

Jean V. Alves, Diogo Leitão, Sérgio Jesus et al.

Public dataset limitations have significantly hindered the development and benchmarking of learning to defer (L2D) algorithms, which aim to optimally combine human and AI capabilities in hybrid decision-making systems. In such systems, human availability and domain-specific concerns introduce difficulties, while obtaining human predictions for training and evaluation is costly. Financial fraud detection is a high-stakes setting where algorithms and human experts often work in tandem; however, there are no publicly available datasets for L2D concerning this important application of human-AI teaming. To fill this gap in L2D research, we introduce the Financial Fraud Alert Review Dataset (FiFAR), a synthetic bank account fraud detection dataset, containing the predictions of a team of 50 highly complex and varied synthetic fraud analysts, with varied bias and feature dependence. We also provide a realistic definition of human work capacity constraints, an aspect of L2D systems that is often overlooked, allowing for extensive testing of assignment systems under real-world conditions. We use our dataset to develop a capacity-aware L2D method and rejection learning approach under realistic data availability conditions, and benchmark these baselines under an array of 300 distinct testing scenarios. We believe that this dataset will serve as a pivotal instrument in facilitating a systematic, rigorous, reproducible, and transparent evaluation and comparison of L2D methods, thereby fostering the development of more synergistic human-AI collaboration in decision-making systems. The public dataset and detailed synthetic expert information are available at: https://github.com/feedzai/fifar-dataset

Sérgio Jesus, Pedro Saleiro, Inês Oliveira e Silva et al.

Aequitas Flow is an open-source framework and toolkit for end-to-end Fair Machine Learning (ML) experimentation, and benchmarking in Python. This package fills integration gaps that exist in other fair ML packages. In addition to the existing audit capabilities in Aequitas, the Aequitas Flow module provides a pipeline for fairness-aware model training, hyperparameter optimization, and evaluation, enabling easy-to-use and rapid experiments and analysis of results. Aimed at ML practitioners and researchers, the framework offers implementations of methods, datasets, metrics, and standard interfaces for these components to improve extensibility. By facilitating the development of fair ML practices, Aequitas Flow hopes to enhance the incorporation of fairness concepts in AI systems making AI systems more robust and fair.

Pedro Saleiro, Benedict Kuester, Loren Hinkson et al.

Recent work has raised concerns on the risk of unintended bias in AI systems being used nowadays that can affect individuals unfairly based on race, gender or religion, among other possible characteristics. While a lot of bias metrics and fairness definitions have been proposed in recent years, there is no consensus on which metric/definition should be used and there are very few available resources to operationalize them. Therefore, despite recent awareness, auditing for bias and fairness when developing and deploying AI systems is not yet a standard practice. We present Aequitas, an open source bias and fairness audit toolkit that is an intuitive and easy to use addition to the machine learning workflow, enabling users to seamlessly test models for several bias and fairness metrics in relation to multiple population sub-groups. Aequitas facilitates informed and equitable decisions around developing and deploying algorithmic decision making systems for both data scientists, machine learning researchers and policymakers.

Pedro Saleiro, Natasa Milic-Frayling, Eduarda Mendes Rodrigues et al.

Improvements of entity-relationship (E-R) search techniques have been hampered by a lack of test collections, particularly for complex queries involving multiple entities and relationships. In this paper we describe a method for generating E-R test queries to support comprehensive E-R search experiments. Queries and relevance judgments are created from content that exists in a tabular form where columns represent entity types and the table structure implies one or more relationships among the entities. Editorial work involves creating natural language queries based on relationships represented by the entries in the table. We have publicly released the RELink test collection comprising 600 queries and relevance judgments obtained from a sample of Wikipedia List-of-lists-of-lists tables. The latter comprise tuples of entities that are extracted from columns and labelled by corresponding entity types and relationships they represent. In order to facilitate research in complex E-R retrieval, we have created and released as open source the RELink Framework that includes Apache Lucene indexing and search specifically tailored to E-R retrieval. RELink includes entity and relationship indexing based on the ClueWeb-09-B Web collection with FACC1 text span annotations linked to Wikipedia entities. With ready to use search resources and a comprehensive test collection, we support community in pursuing E-R research at scale.

João Bravo, Jacopo Bono, Pedro Saleiro et al.

Systems characterized by evolving interactions, prevalent in social, financial, and biological domains, are effectively modeled as continuous-time dynamic graphs (CTDGs). To manage the scale and complexity of these graph datasets, machine learning (ML) approaches have become essential. However, CTDGs pose challenges for ML because traditional static graph methods do not naturally account for event timings. Newer approaches, such as graph recurrent neural networks (GRNNs), are inherently time-aware and offer advantages over static methods for CTDGs. However, GRNNs face another issue: the short truncation of backpropagation-through-time (BPTT), whose impact has not been properly examined until now. In this work, we demonstrate that this truncation can limit the learning of dependencies beyond a single hop, resulting in reduced performance. Through experiments on a novel synthetic task and real-world datasets, we reveal a performance gap between full backpropagation-through-time (F-BPTT) and the truncated backpropagation-through-time (T-BPTT) commonly used to train GRNN models. We term this gap the "truncation gap" and argue that understanding and addressing it is essential as the importance of CTDGs grows, discussing potential future directions for research in this area.

Ricardo Moreira, Jacopo Bono, Mário Cardoso et al.

Model interpretability plays a central role in human-AI decision-making systems. Ideally, explanations should be expressed using human-interpretable semantic concepts. Moreover, the causal relations between these concepts should be captured by the explainer to allow for reasoning about the explanations. Lastly, explanation methods should be efficient and not compromise the performance of the predictive task. Despite the rapid advances in AI explainability in recent years, as far as we know to date, no method fulfills these three properties. Indeed, mainstream methods for local concept explainability do not produce causal explanations and incur a trade-off between explainability and prediction performance. We present DiConStruct, an explanation method that is both concept-based and causal, with the goal of creating more interpretable local explanations in the form of structural causal models and concept attributions. Our explainer works as a distillation model to any black-box machine learning model by approximating its predictions while producing the respective explanations. Because of this, DiConStruct generates explanations efficiently while not impacting the black-box prediction task. We validate our method on an image dataset and a tabular dataset, showing that DiConStruct approximates the black-box models with higher fidelity than other concept explainability baselines, while providing explanations that include the causal relations between the concepts.

Catarina Belém, Vladimir Balayan, Pedro Saleiro et al.

In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations based on model features. To obtain faithful concept-based explanations, we leverage multi-task learning to train a neural network that jointly learns to predict a decision task based on the predictions of a precedent explainability task (i.e., multi-label concepts). There are two main challenges to overcome: concept label scarcity and the joint learning. To address both, we propose to: i) use expert rules to generate a large dataset of noisy concept labels, and ii) apply two distinct multi-task learning strategies combining noisy and golden labels. We compare these strategies with a fully supervised approach in a real-world fraud detection application with few golden labels available for the explainability task. With improvements of 9.26% and of 417.8% at the explainability and decision tasks, respectively, our results show it is possible to improve performance at both tasks by combining labels of heterogeneous quality.

André F. Cruz, Pedro Saleiro, Catarina Belém et al.

Considerable research effort has been guided towards algorithmic fairness but real-world adoption of bias reduction techniques is still scarce. Existing methods are either metric- or model-specific, require access to sensitive attributes at inference time, or carry high development or deployment costs. This work explores the unfairness that emerges when optimizing ML models solely for predictive performance, and how to mitigate it with a simple and easily deployed intervention: fairness-aware hyperparameter optimization (HO). We propose and evaluate fairness-aware variants of three popular HO algorithms: Fair Random Search, Fair TPE, and Fairband. We validate our approach on a real-world bank account opening fraud case-study, as well as on three datasets from the fairness literature. Results show that, without extra training cost, it is feasible to find models with 111% mean fairness increase and just 6% decrease in performance when compared with fairness-blind HO.

Sérgio Jesus, Catarina Belém, Vladimir Balayan et al.

There have been several research works proposing new Explainable AI (XAI) methods designed to generate model explanations having specific properties, or desiderata, such as fidelity, robustness, or human-interpretability. However, explanations are seldom evaluated based on their true practical impact on decision-making tasks. Without that assessment, explanations might be chosen that, in fact, hurt the overall performance of the combined system of ML model + end-users. This study aims to bridge this gap by proposing XAI Test, an application-grounded evaluation methodology tailored to isolate the impact of providing the end-user with different levels of information. We conducted an experiment following XAI Test to evaluate three popular post-hoc explanation methods -- LIME, SHAP, and TreeInterpreter -- on a real-world fraud detection task, with real data, a deployed ML model, and fraud analysts. During the experiment, we gradually increased the information provided to the fraud analysts in three stages: Data Only, i.e., just transaction data without access to model score nor explanations, Data + ML Model Score, and Data + ML Model Score + Explanations. Using strong statistical analysis, we show that, in general, these popular explainers have a worse impact than desired. Some of the conclusion highlights include: i) showing Data Only results in the highest decision accuracy and the slowest decision time among all variants tested, ii) all the explainers improve accuracy over the Data + ML Model Score variant but still result in lower accuracy when compared with Data Only; iii) LIME was the least preferred by users, probably due to its substantially lower variability of explanations from case to case.

João Bento, Pedro Saleiro, André F. Cruz et al.

Although recurrent neural networks (RNNs) are state-of-the-art in numerous sequential decision-making tasks, there has been little research on explaining their predictions. In this work, we present TimeSHAP, a model-agnostic recurrent explainer that builds upon KernelSHAP and extends it to the sequential domain. TimeSHAP computes feature-, timestep-, and cell-level attributions. As sequences may be arbitrarily long, we further propose a pruning method that is shown to dramatically decrease both its computational cost and the variance of its attributions. We use TimeSHAP to explain the predictions of a real-world bank account takeover fraud detection RNN model, and draw key insights from its explanations: i) the model identifies important features and events aligned with what fraud analysts consider cues for account takeover; ii) positive predicted sequences can be pruned to only 10% of the original length, as older events have residual attribution values; iii) the most recent input event of positive predictions only contributes on average to 41% of the model's score; iv) notably high attribution to client's age, suggesting a potential discriminatory reasoning, later confirmed as higher false positive rates for older clients.

Vladimir Balayan, Pedro Saleiro, Catarina Belém et al.

Machine Learning (ML) has been increasingly used to aid humans to make better and faster decisions. However, non-technical humans-in-the-loop struggle to comprehend the rationale behind model predictions, hindering trust in algorithmic decision-making systems. Considerable research work on AI explainability attempts to win back trust in AI systems by developing explanation methods but there is still no major breakthrough. At the same time, popular explanation methods (e.g., LIME, and SHAP) produce explanations that are very hard to understand for non-data scientist persona. To address this, we present JOEL, a neural network-based framework to jointly learn a decision-making task and associated explanations that convey domain knowledge. JOEL is tailored to human-in-the-loop domain experts that lack deep technical ML knowledge, providing high-level insights about the model's predictions that very much resemble the experts' own reasoning. Moreover, we collect the domain feedback from a pool of certified experts and use it to ameliorate the model (human teaching), hence promoting seamless and better suited explanations. Lastly, we resort to semantic mappings between legacy expert systems and domain taxonomies to automatically annotate a bootstrap training set, overcoming the absence of concept-based human annotations. We validate JOEL empirically on a real-world fraud detection dataset. We show that JOEL can generalize the explanations from the bootstrap dataset. Furthermore, obtained results indicate that human teaching can further improve the explanations prediction quality by approximately $13.57\%$.

André F. Cruz, Pedro Saleiro, Catarina Belém et al.

Considerable research effort has been guided towards algorithmic fairness but there is still no major breakthrough. In practice, an exhaustive search over all possible techniques and hyperparameters is needed to find optimal fairness-accuracy trade-offs. Hence, coupled with the lack of tools for ML practitioners, real-world adoption of bias reduction methods is still scarce. To address this, we present Fairband, a bandit-based fairness-aware hyperparameter optimization (HO) algorithm. Fairband is conceptually simple, resource-efficient, easy to implement, and agnostic to both the objective metrics, model types and the hyperparameter space being explored. Moreover, by introducing fairness notions into HO, we enable seamless and efficient integration of fairness objectives into real-world ML pipelines. We compare Fairband with popular HO methods on four real-world decision-making datasets. We show that Fairband can efficiently navigate the fairness-accuracy trade-off through hyperparameter optimization. Furthermore, without extra training cost, it consistently finds configurations attaining substantially improved fairness at a comparatively small decrease in predictive accuracy.

Pedro Saleiro, Natasa Milic-Frayling, Eduarda Mendes Rodrigues et al.

Entity-Relationship (E-R) Search is a complex case of Entity Search where the goal is to search for multiple unknown entities and relationships connecting them. We assume that a E-R query can be decomposed as a sequence of sub-queries each containing keywords related to a specific entity or relationship. We adopt a probabilistic formulation of the E-R search problem. When creating specific representations for entities (e.g. context terms) and for pairs of entities (i.e. relationships) it is possible to create a graph of probabilistic dependencies between sub-queries and entity plus relationship representations. To the best of our knowledge this represents the first probabilistic model of E-R search. We propose and develop a novel supervised Early Fusion-based model for E-R search, the Entity-Relationship Dependence Model (ERDM). It uses Markov Random Field to model term dependencies of E-R sub-queries and entity/relationship documents. We performed experiments with more than 800M entities and relationships extractions from ClueWeb-09-B with FACC1 entity linking. We obtained promising results using 3 different query collections comprising 469 E-R queries, with results showing that it is possible to perform E-R search without using fix and pre-defined entity and relationship types, enabling a wide range of queries to be addressed.

Pedro Saleiro

Online Reputation Monitoring (ORM) is concerned with the use of computational tools to measure the reputation of entities online, such as politicians or companies. In practice, current ORM methods are constrained to the generation of data analytics reports, which aggregate statistics of popularity and sentiment on social media. We argue that this format is too restrictive as end users often like to have the flexibility to search for entity-centric information that is not available in predefined charts. As such, we propose the inclusion of entity retrieval capabilities as a first step towards the extension of current ORM capabilities. However, an entity's reputation is also influenced by the entity's relationships with other entities. Therefore, we address the problem of Entity-Relationship (E-R) retrieval in which the goal is to search for multiple connected entities. This is a challenging problem which traditional entity search systems cannot cope with. Besides E-R retrieval we also believe ORM would benefit of text-based entity-centric prediction capabilities, such as predicting entity popularity on social media based on news events or the outcome of political surveys. However, none of these tasks can provide useful results if there is no effective entity disambiguation and sentiment analysis tailored to the context of ORM. Consequently, this thesis address two computational problems in Online Reputation Monitoring: Entity Retrieval and Text Mining. We researched and developed methods to extract, retrieve and predict entity-centric information spread across the Web.

Pedro Saleiro, Luís Sarmento, Eduarda Mendes Rodrigues et al.

This paper describes a preliminary study for producing and distributing a large-scale database of embeddings from the Portuguese Twitter stream. We start by experimenting with a relatively small sample and focusing on three challenges: volume of training data, vocabulary size and intrinsic evaluation metrics. Using a single GPU, we were able to scale up vocabulary size from 2048 words embedded and 500K training examples to 32768 words over 10M training examples while keeping a stable validation loss and approximately linear trend on training time per epoch. We also observed that using less than 50\% of the available training examples for each vocabulary size might result in overfitting. Results on intrinsic evaluation show promising performance for a vocabulary size of 32768 words. Nevertheless, intrinsic evaluation metrics suffer from over-sensitivity to their corresponding cosine similarity thresholds, indicating that a wider range of metrics need to be developed to track progress.

Pedro Saleiro, Natasa Milic-Frayling, Eduarda Mendes Rodrigues et al.

We address the task of entity-relationship (E-R) retrieval, i.e, given a query characterizing types of two or more entities and relationships between them, retrieve the relevant tuples of related entities. Answering E-R queries requires gathering and joining evidence from multiple unstructured documents. In this work, we consider entity and relationships of any type, i.e, characterized by context terms instead of pre-defined types or relationships. We propose a novel IR-centric approach for E-R retrieval, that builds on the basic early fusion design pattern for object retrieval, to provide extensible entity-relationship representations, suitable for complex, multi-relationships queries. We performed experiments with Wikipedia articles as entity representations combined with relationships extracted from ClueWeb-09-B with FACC1 entity linking. We obtained promising results using 3 different query collections comprising 469 E-R queries.

Pedro Saleiro, Eduarda Mendes Rodrigues, Carlos Soares et al.

This paper presents the approach developed at the Faculty of Engineering of University of Porto, to participate in SemEval 2017, Task 5: Fine-grained Sentiment Analysis on Financial Microblogs and News. The task consisted in predicting a real continuous variable from -1.0 to +1.0 representing the polarity and intensity of sentiment concerning companies/stocks mentioned in short texts. We modeled the task as a regression analysis problem and combined traditional techniques such as pre-processing short texts, bag-of-words representations and lexical-based features with enhanced financial specific bag-of-embeddings. We used an external collection of tweets and news headlines mentioning companies/stocks from S\&P 500 to create financial word embeddings which are able to capture domain-specific syntactic and semantic similarities. The resulting approach obtained a cosine similarity score of 0.69 in sub-task 5.1 - Microblogs and 0.68 in sub-task 5.2 - News Headlines.

Daniela Ulloa, Pedro Saleiro, Rosaldo J. F. Rossetti et al.

This work proposes a novel framework for the development of new products and services in transportation through an open innovation approach based on automatic content analysis of social media data. The framework is able to extract users comments from Online Social Networks (OSN), to process and analyze text through information extraction and sentiment analysis techniques to obtain relevant information about product reception on the market. A use case was developed using the mobile application Uber, which is today one of the fastest growing technology companies in the world. We measured how a controversial, highly diffused event influences the volume of tweets about Uber and the perception of its users. While there is no change in the image of Uber, a large increase in the number of tweets mentioning the company is observed, which meant a free and important diffusion of its product.

João Oliveira, Mike Pinto, Pedro Saleiro et al.

Social Media users tend to mention entities when reacting to news events. The main purpose of this work is to create entity-centric aggregations of tweets on a daily basis. By applying topic modeling and sentiment analysis, we create data visualization insights about current events and people reactions to those events from an entity-centric perspective.

Pedro Saleiro, Jorge Teixeira, Carlos Soares et al.

We present a dynamic web tool that allows interactive search and visualization of large news archives using an entity-centric approach. Users are able to search entities using keyword phrases expressing news stories or events and the system retrieves the most relevant entities to the user query based on automatically extracted and indexed entity profiles. From the computational journalism perspective, TimeMachine allows users to explore media content through time using automatic identification of entity names, jobs, quotations and relations between entities from co-occurrences networks extracted from the news articles. TimeMachine demo is available at http://maquinadotempo.sapo.pt/

Pedro Saleiro, Luís Sarmento

Encyclopedic queries express the intent of obtaining information typically available in encyclopedias, such as biographical, geographical or historical facts. In this paper, we train a classifier for detecting the encyclopedic intent of web queries. For training such a classifier, we automatically label training data from raw query logs. We use click-through data to select positive examples of encyclopedic queries as those queries that mostly lead to Wikipedia articles. We investigated a large set of features that can be generated to describe the input query. These features include both term-specific patterns as well as query projections on knowledge bases items (e.g. Freebase). Results show that using these feature sets it is possible to achieve an F1 score above 87%, competing with a Google-based baseline, which uses a much wider set of signals to boost the ranking of Wikipedia for potential encyclopedic queries. The results also show that both query projections on Wikipedia article titles and Freebase entity match represent the most relevant groups of features. When the training set contains frequent positive examples (i.e rare queries are excluded) results tend to improve.