Twitter should be an ideal place to get a fresh read on how different issues are playing with the public, one that's potentially more reflective of democracy in this new media age than traditional polls. Pollsters typically ask people a fixed set of questions, while in social media people use their own voices to speak about whatever is on their minds. However, the demographic distribution of users on Twitter is not representative of the general population. In this paper, we present a demographic classifier for gender, age, political orientation and location on Twitter. We collected and curated a robust Twitter demographic dataset for this task. Our classifier uses a deep multi-modal multitask learning architecture to reach a stateof-the-art performance, achieving an F1-score of 0.89, 0.82, 0.86, and 0.68 for gender, age, political orientation, and location respectively.

This paper describes our approach for the Detecting Stance in Tweets task (SemEval-2016 Task 6). We utilized recent advances in short text categorization using deep learning to create word-level and character-level models. The choice between word-level and characterlevel models in each particular case was informed through validation performance. Our final system is a combination of classifiers using word-level or character-level models. We also employed novel data augmentation techniques to expand and diversify our training dataset, thus making our system more robust. Our system achieved a macro-average precision, recall and F1-scores of 0.67, 0.61 and 0.635 respectively.

Hemodialysis (HD) in neonates and infants poses unique challenges due to high risks of mortality attributable to obligatory small blood flow volumes. Although HD is often necessary in neonates, its effectiveness and feasibility are poorly understood. The aim of this review is to describe in detail the few studies reporting on HD in neonates and infants (<12 months old) and then dissertate more broadly on the subject with an emphasis on recent innovations with potential to overcome traditional barriers for effective HD in this population. We detail the clinical characteristics, outcomes, technical considerations, maintenance and complications associated with HD, and provide guidance for addressing challenges associated with HD in this population.

We present Tweet2Vec, a novel method for generating generalpurpose vector representation of tweets. The model learns tweet embeddings using character-level CNN-LSTM encoderdecoder. We trained our model on 3 million, randomly selected English-language tweets. The model was evaluated using two methods: tweet semantic similarity and tweet sentiment categorization, outperforming the previous state-ofthe-art in both tasks. The evaluations demonstrate the power of the tweet embeddings generated by our model for various tweet categorization tasks. The vector representations generated by our model are generic, and hence can be applied to a variety of tasks. Though the model presented in this paper is trained on English-language tweets, the method presented can be used to learn tweet embeddings for different languages.

The ability to infer persona from dialogue can have applications in areas ranging from computational narrative analysis to personalized dialogue generation. We introduce neural models to learn persona embeddings in a supervised character trope classification task. The models encode dialogue snippets from IMDB into representations that can capture the various categories of film characters. The bestperforming models use a multi-level attention mechanism over a set of utterances. We also utilize prior knowledge in the form of textual descriptions of the different tropes. We apply the learned embeddings to find similar characters across different movies, and cluster movies according to the distribution of the embeddings. The use of short conversational text as input, and the ability to learn from prior knowledge using memory, suggests these methods could be applied to other domains. * The first two authors contributed equally to this work. sense personality in order to generate more interesting and varied conversations.

No abstract

No abstract

PurposeCustomer support assumes strategic importance in India for branded IT‐hardware products. An authorized service center and a stream of specialized service centers undertake field services and represent a sale‐territory's support network. “Time constrained” service men have to deliver customized service meeting a promised time‐standard. The stochastic demand for support services severely mars the customer response resulting in poor service quality. A manufacturer has to address the following decisions under these conditions: what is the ideal staffing level in a territory considering restricted server availability? What will be the impact of changing the staffing levels on customer service level? This study develops an analytical model to address these decisions.Design/methodology/approachThe study identifies the variables underlying stochastic service demand through a field survey and determines the demand distribution. Applying stochastic principles the study derives relation between field staffing level and customer response considering server time constraint. Study performs statistical analysis to validate this model with real time data on variables collected from the field survey.FindingsThe outcomes of analysis reveal the following findings: this model can be applied in service systems where a time constrained server has to deliver expected level of performance (research implication); and increasing field staffing levels obscures the significant difference between the customer waiting times under very high levels of uncertain demand (practical implication).Originality/valueThe study derives relation between the staffing levels and customer waiting time considering uncertain demand with restricted working hour conditions.