Chrysoula Zerva & Mustafa A. Mustafa Workshop

Time: 11:30 to 12:30

Venue: Williamson Building, G47

Sorry, this event has now ended.

Chrysoula Zerva - Postdoctoral Researcher in Computer Science

Assessing credibility of health & science news via scientific literature

News on scientific advances, health issues and technological miracles have always been among the most viral and controversial ones, both because of the potential impact on people's lives and because often, the communicated knowledge is complex and hard to verify. Much like political news, health and science news often contain exaggerated statements, misinterpreted statistics and information taken out of context. Thus evaluating the trustworthiness of an article and the credibility of provided information is an involved procedure, requiring both evaluation of the scientific literature and comparison with the information in the original article. Such a process is often too laborious and time consuming to be manually performed by experts, and too demanding for the lay readers. Thus, leveraging information from scientific literature and using it to assess science and health news articles in an automated way could alleviate the issue and help readers and authors alike.
We present some initial efforts on mapping news information to scientific information, using a mixture of deep learning and traditional machine learning approaches. We discuss points of failure for the initial architecture, and propose a new end-to-end framework. The latter uses graph embeddings to achieve an optimal matching between context of sentences across documents and a multi-task architecture, aiming to use heterogeneous information in order to predict the credibility of a news article. We show how we aim to take advantage of manually scored articles for credibility (healthfeedback.org). We also discuss a crowdsourcing plan for further annotations to support deep learning for credibility identification in science news based on BBC articles.

Mustafa A. Mustafa - Dame Kathleen Ollerenshaw Research Fellow in Computer Science

Secure and privacy-friendly peer-to-peer energy trading

A peer-to-peer electricity market allows users to trade electricity among themselves and increases their financial well-being. In addition, electricity exchange between nearby users can significantly reduce the electricity loss during transmission over the distribution lines. Bids and offers in such a market can be created from a heterogeneous set of generation devices, such as PV, storage devices, such as batteries, and flexible loads, such as electric boilers. 

However, such markets may also create an opportunity for malicious entities to misbehave in order to reduce costs or maximise profits. Potential threats are impersonation, data manipulation, eavesdropping, disputes, and privacy breaches. Moreover, the shifting responsibilities brought about by local trading necessitate fundamental research into the application of centralised regulatory regimes such as European data protection law and network and information security (NIS) law. Both legal regimes have undergone notable reforms, with the adoption of the General Data Protection Regulation (GDPR) and the NIS Directive, which will be transposed into Member State law as of 2018. As an example of a privacy breach, consider entities which have access to users' offers and bids. They may use this data to infer who is selling or buying how much electricity and when. Such data is closely correlated to users' consumption patterns, which potentially reveal sensitive information; and which may facilitate consumer profiling by fingerprinting and tracking the use of specific electronic appliances. 

In this talk, I will give a short overview of the SNIPPET project and it goals (video), as well as, some initial results of our efforts to design secure and privacy-friendly billing and settlement mechanisms between users, suppliers and grid operators in such p2p energy trading markets.

If you are interested in discussing your research at future sessions, please contact:
david.builgil@manchester.ac.uk or michael.prentice@manchester.ac.uk