Social reputation (e.g., likes, comments, shares, etc.) on YouTube is the primary tenet to popularize channels/videos. However, the organic way to improve social reputation is tedious, which often provokes content creators to seek services of online blackmarkets for rapidly inflating content reputation. Such blackmarkets act underneath a thriving collusive ecosystem comprising core users and compromised accounts (together known as collusive users). Core users form the backbone of blackmarkets; thus, spotting and suspending them may help in destabilizing the entire collusive network. Although a few studies focused on collusive user detection on Twitter, Facebook, and YouTube, none of them differentiate between core users and compromised accounts.
We are the first to present a rigorous analysis of core users in YouTube blackmarkets. To this end, we collect a new dataset of collusive YouTube users. We study the core-periphery structure of the underlying collusive commenting network (CCN). We examine the topology of CCN to explore the behavioral dynamics of core and compromised users. We then introduce KORSE, a novel graph-based method to automatically detect core users based only on the topological structure of CCN. KORSE performs a weighted k-core decomposition using our proposed metric, called Weighted Internal Core Collusive Index (WICCI). However, KORSE is infeasible to adopt in practice as it requires complete interactions among collusive users to construct CCN. We, therefore, propose NURSE, a deep fusion framework that only leverages user timelines (without considering the underlying CCN) to detect core blackmarket users. Experimental results show that NURSE is quite close to KORSE in detecting core users and outperforms nine baselines.

Weakening the Inner Strength: Spotting Core Collusive Users in YouTube Blackmarket Network

Currently, publicly available models for website classification do not offer an embedding method and have limited support for languages beyond English. We release a dataset with more than 1M websites in 92 languages with relative labels collected from Curlie, the largest multilingual crowdsourced Web directory. The dataset contains 14 website categories aligned across languages. Alongside it, we introduce Homepage2Vec, a machine-learned pre-trained model for classifying and embedding websites based on their homepage in a language-agnostic way. Homepage2Vec, thanks to its feature set (textual content, metadata tags, and visual attributes) and recent progress in natural language representation, is language-independent by design and can generate embeddings representation. We show that Homepage2Vec correctly classifies websites with a macro-averaged F1-score of 0.90, with stable performance across low- as well as high-resource languages. Feature analysis shows that a small subset of efficiently computable features suffices to achieve high performance even with limited computational resources. 
We make publicly available the curated Curlie dataset aligned across languages, the pre-trained Homepage2Vec model, and libraries.

Language-Agnostic Website Embedding and Classification

Existing self-explaining models typically favor extracting the shortest possible rationales — snippets of an input text “responsible for” corresponding output — to explain the model prediction, with the assumption that shorter rationales are more intuitive to humans. How- ever, this assumption has yet to be validated. Is the shortest rationale indeed the most human- understandable? To answer this question, we design a self-explaining model, LimitedInk, which allows users to extract rationales at any target length. Compared to existing baselines, LimitedInk achieves compatible end- task performance and human-annotated rationale agreement, making it a suitable representation of the recent class of self-explaining models. We use LimitedInk to conduct a user study on the impact of rationale length, where we ask human judges to predict the sentiment label of documents based only on LimitedInk- generated rationales with different lengths. We show rationales that are too short do not help humans predict labels better than randomly masked text, suggesting the need for more careful design of the best human rationales

Are Shortest Rationales the Best Explanations for Human Understanding?

Computação Afetiva na Web

Sistemas de Recomendação na Globo: algorítmos, desafios e tendências

The power of graphs in immersive communications

Como podemos moldar o futuro do Brasil por meio de design e tecnologia integrados à logística?

In this paper we present SPRING Online Services, a Web interface and RESTful APIs
for our state-of-the-art AMR parsing and generation system, SPRING (Symmetric PaRsIng aNd Generation). 
The Web interface has been developed to be easily used by the Natural Language Processing community, as well as by the general public. 
It provides, among other things, a highly interactive visualization platform and a feedback mechanism to obtain user suggestions for further improvements of the system's output. 
Moreover, our RESTful APIs enable easy integration of SPRING in downstream applications where AMR structures are needed.
Finally, we make SPRING Online Services freely available at http://nlp.uniroma1.it/spring and, in addition, we release extra model checkpoints to be used with the original SPRING Python code.

SPRING Goes Online: End-to-End AMR Parsing and Generation

Não acredite em tudo que você lê!" — Desinformação na Web: Desafios, Análises e Resultados

The presentation gives a overview of universal meaning representations(UMR), presents the challenges of designing a tool to annotate UMR and how to address them. The presentation also includes a system demo.

UMR-Writer: A Web Application for Annotating Uniform Meaning Representations

In agribusiness, the treatment and sustainable management of waste in intensive production systems must consider productivity and economic gains in the short term and the sustainability of agricultural production. The acquisition of technical information, and the knowledge about the characteristics of the rural property, are
fundamental for stakeholders, especially considering the adequacy of sustainable environmental practices. It is necessary to provide a web-based system to support stakeholders in discovering and understanding their productive context. This paper proposes a solution to support stakeholders’ decision-making to improve sustainable
practices in agribusiness. The proposed solution is applied in the agricultural domain, focusing on sustainability, by implementing a web system supported by an ontology to organize and provide strategic information through a mobile app. Technical and regulatory environmental practices documents are recommended for a relevant context, considering a feasibility study with experts in the field. As a result, the approach provided decision-making support offering technical information efficiently and agile for stakeholders.

@grogest_Ambiental: A Web-based Decision Support System for agribusiness

Widgets are part of many web applications and implement distinct interaction mechanisms, in reusable user interface components.
However, implementing accessible widgets is a challenge, associated to different factors highlighted in the state-of-the-art, such as: lack of developers knowledge of accessibility guidelines, organization support and tools that support accessible development.
This paper reports an investigation on JavaScript source-code complexity impacts of implementing accessibility requirements in widgets.
We investigated Dialog, Drop-down menu and Tab widgets of 27 open-source JavaScript libraries.
The results showed that widget software artifacts reported an increased average of source-code complexity when implementing accessibility requirements.
Results also showed that using DOM-oriented JavaScript libraries (eg. jQuery) significantly increased source-code complexity of widgets.
Nevertheless, when using Declarative Component-based JavaScript libraries, no significant difference in source-code complexity was observed.
These results suggest that using Declarative Component-based widget libraries might reduce maintainability costs of JavaScript front-end projects.

Underline digital video library

Weakening the Inner Strength: Spotting Core Collusive Users in YouTube Blackmarket Network

Language-Agnostic Website Embedding and Classification

Are Shortest Rationales the Best Explanations for Human Understanding?

Computação Afetiva na Web

Sistemas de Recomendação na Globo: algorítmos, desafios e tendências

The power of graphs in immersive communications

Como podemos moldar o futuro do Brasil por meio de design e tecnologia integrados à logística?

SPRING Goes Online: End-to-End AMR Parsing and Generation

Não acredite em tudo que você lê!" — Desinformação na Web: Desafios, Análises e Resultados

UMR-Writer: A Web Application for Annotating Uniform Meaning Representations

@grogest_Ambiental: A Web-based Decision Support System for agribusiness

Code Complexity Impact of Widgets Accessibility Implementation in JavaScript Open-Source Libraries

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES