Evaluation of information extraction techniques to label extracted data from e-commerce web page

Automatically determining and assigning shared and meaningful text labels to data extracted from an e-Commerce web page is a challenging problem. An e-Commerce web page can display a list of data records, each of which can contain a combination of data items (e.g. product name and price) and explicit labels, which describe some of these data items. Recent advances in extraction techniques have made it much easier to precisely extract individual data items and labels from a web page, however, there are two open problems: 1. assigning an explicit label to a data item, and 2. determining labels for the remaining data items. Furthermore, improvements in the availability and coverage of vocabularies, especially in the context of e-Commerce web sites, means that we now have access to a bank of relevant, meaningful and shared labels which can be assigned to extracted data items. However, there is a need for a technique which will take as input a set of extracted data items and assign automatically to them the most relevant and meaningful labels from a shared vocabulary. We observe that the Information Extraction (IE) community has developed a great number of techniques which solve problems similar to our own. In this work-in-progress paper we propose our intention to theoretically and experimentally evaluate different IE techniques to ascertain which is most suitable to solve this problem.

Label-free Analysis of Conformational Dynamics and Molecular Interaction of Biomolecules by Vis-NIR Metasensor

Analysis of binding recognition and conformation of biomolecules is of paramount important in understanding of their vital functions in complex biological systems. By enabling sub-wavelength light localization and strong local field enhancement, plasmonic biosensors have become dominant tools used for such analysis owing to their label-free and real-time attributes1,2. However, the plasmonic biosensors are not well-suited to provide information regarding conformation or chemical fingerprint of biomolecules. Here, we show that plasmonic metamaterials, consisting of periodic arrays of artificial split-ring resonators (SRRs)3, can enable capabilities of both sensing and fingerprinting of biomolecules. We demonstrate that by engineering geometry of individual SRRs, localized surface plasmon resonance (LSPR) frequency of the metamaterials could be tuned to visible-near infrared regimes (Vis-NIR) such that they possess high local field enhancement for surface-enhanced Raman scattering spectroscopy (SERS). This will provide the basis for the development of a dual mode label-free conformational-resolving and quantitative detection platform. We present here the ability of each sensing mode to independently detect binding adsorption and to identify different conformational states of Guanine (G)-rich DNA monolayers in different environment milieu. Also shown is the use of the nanosensor for fingerprinting and detection of Arginine-Glycine-Glycine (RGG) peptide binding to the G-quadruplex aptamer. The dual-mode nanosensor will significantly contribute to unraveling the complexes of the conformational dynamics of biomolecules as well as to improving specificity of biodetection assays that the conventional, population-averaged plasmonic biosensors cannot achieve.

Twitter Sentiment Analysis for Security-Related Information Gathering

Analysing public sentiment about future events, such as demonstration or parades, may provide valuable information while estimating the level of disruption and disorder during these events. Social media, such as Twitter or Facebook, provides views and opinions of users related to any public topics. Consequently, sentiment analysis of social media content may be of interest to different public sector organisations, especially in the security and law enforcement sector. In this paper we present a lexicon-based approach to sentiment analysis of Twitter content. The algorithm performs normalisation of the sentiment in an effort to provide intensity of the sentiment rather than positive/negative label. Following this, we evaluate an evidence-based combining function that supports the classification process in cases when positive and negative words co-occur in a tweet. Finally, we illustrate a case study examining the relation between sentiment of twitter posts related to English Defence League and the level of disorder during the EDL related events.