The abundance of text available in social media and health related forums along with the rich expression public opinion have recently attracted interest community to use these sources for pharmacovigilance. Based on intuition that patients post about Adverse Drug Reactions (ADRs) expressing negative sentiments, we investigate effect sentiment analysis features locating ADR mentions. We enrich feature space a state-of-the-art identification method features. Using corpus posts from...

Online Social Media platforms, such as Facebook and Twitter, enable all users, independently of their characteristics, to freely generate consume huge amounts data. While this data is being exploited by individuals organisations gain competitive advantage, a substantial amount generated spam or fake users. One in every 200 social media messages one 21 tweets estimated be spam. The rapid growth the volume global expected compromise research works that use data, thereby questioning...

Learning from outliers and imbalanced data remains one of the major difficulties for machine learning classifiers. Among numerous techniques dedicated to tackle this problem, preprocessing solutions are known be efficient easy implement. In paper, we propose a selective approach that embeds knowledge outlier instances into artificially generated subset achieve an even distribution. The Synthetic Minority Oversampling TEchnique (SMOTE) was used balance training by introducing artificial...

Social media are well-established means of online communication, generating vast amounts data. In this paper, we focus on Twitter and investigate behavioural differences between male female users social media. Using Natural Language Processing Machine Learning approaches, propose a user gender identification method that considers both the tweets profile description user. For experimentation evaluation, enriched used an existing User Gender Classification dataset, which is freely available...

Background and Objectives Declining mental health is a prominent concerning issue. Affective classification, which employs machine learning on brain signals captured from electroencephalogram (EEG), prevalent approach to address this However, many existing studies have adopted one-size-fits-all approach, where data multiple individuals are combined create single "generic" classification model. This overlooks individual differences may not accurately capture the unique emotional patterns of...

Drug named entity recognition (NER) is a critical step for complex biomedical NLP tasks such as the extraction of pharmacogenomic, pharmacodynamic and pharmacokinetic parameters. Large quantities high quality training data are almost always prerequisite employing supervised machine-learning techniques to achieve classification performance. However, human labour needed produce maintain resources significant limitation. In this study, we improve performance drug NER without relying exclusively...

The manuscript presents a case of 29-year-old pregnant woman who developed severe psychotic episode during the second trimester her pregnancy. Bipolar disorder (BD) is serious mood uncertain etiology marked by significant and long-lasting fluctuations in mood. It major cause disability worldwide, with higher rate progression frequency women. Pregnancy represents vulnerable period for women BD, as hormonal psychological changes can trigger episodes. Pharmacological treatment was given,...

A forum or social media post can express multiple emotions, such as love, joy anger. Emotion classification has been proven useful for measuring aspects user satisfaction. Despite its usefulness, research in emotion is limited, because the task multi-label and publicly available data sets lexica are very limited. number of classifiers general-domain text have proposed recently, but only a few domain Open Source Software (OSS), EmoTxt. In this paper, we explore different two algorithms...

Natural Language Processing (NLP) is the sub-field of Artificial Intelligence that represents and analyses human language automatically. NLP has been employed in many applications, such as information retrieval, processing automated answer ranking. Semantic analysis focuses on understanding meaning text. Among other proposed approaches, Latent Analysis (LSA) a widely used corpus-based approach evaluates similarity text based semantic relations among words. LSA applied successfully diverse...

Citation screening is a labour-intensive part of the process systematic literature review that identifies citations eligible for inclusion in review. In this paper, we present an automatic text classification approach aims to prioritise earlier than ineligible ones and thus reduces manual labelling effort involved process. e.g. by automatically excluding lower ranked citations. To improve performance classifier, develop novel neural network-based feature extraction method. Unlike previous...

Heterotopic triplet pregnancy is an exceptionally rare medical condition. The broad use of assisted reproductive technologies has contributed to the increase ectopic and subsequently heterotopic rate, masking a life-threatening condition for gravid intrauterine pregnancy. We describe case woman with triplets at 9 +4 gestational week following transfer three embryos obtained by in vitro fertilization techniques. tubal was ruptured salpingectomy performed laparotomy. progressed delivery...

A network is a composition of many communities, i.e., sets nodes and edges with stronger relationships, distinct overlapping properties. Community detection crucial for various reasons, such as serving functional unit that captures local interactions among nodes. Communities come in forms types, ranging from biologically to technology-induced ones. As social media networks Twitter Facebook connect myriad diverse users, leading highly connected dynamic ecosystem. Although algorithms have been...

Clinical trials are mandatory protocols describing medical research on humans and among the most valuable sources of practice evidence. Searching for relevant to some query is laborious due immense number existing protocols. Apart from search, writing new includes composing detailed eligibility criteria, which might be time-consuming, especially researchers. In this paper we present ASCOT, an efficient search application customised clinical trials. ASCOT uses text mining data methods enrich...

Fibroepithelial stromal polyps (FEPs) are benign skin tumors or lesions of mesenchymal and ectodermal origin, also referred to as acrochordons. Herein, we report the case a 45-year-old woman with large ulcerated fibroepithelial polyp extending from right labium vulva. No known predisposing factor was recorded justify presence rapid growth polyp. Antibiotic treatment given due inflammation, magnetic resonance imaging useful in establishing diagnosis. A wide surgical excision performed,...

Identifying whether a multi-word expression (MWE) is compositional or not important for numerous NLP applications. Sense induction can partition the context of MWEs into semantic uses and therefore aid in deciding compositionality. We propose an unsupervised system to explore this hypothesis on compound nominals, proper names adjective-noun constructions, evaluate contribution sense induction. The evaluation set derived from WordNet semisupervised way. Graph connectivity measures are...

The vast numbers of digitised documents containing historical data constitute a rich research repository. However, computational methods and tools available to explore this are still limited in functionality. Research on archives is largely carried out manually. Text mining technologies offer novel analyse digital content identify various types semantic information these extract them as metadata. Methods range from the automatic identification named entities (e.g., people, places,...