Search

To characterize retinal tears (RTs) and calculate the economic burden of RTs that present to the emergency department (ED) in the US. We used a large national ED database to retrospectively analyze RTs that presented to the ED from 2006 to 2019. Using extrapolation methods, national of the RT patient ED volume, demographics, comorbidities, disposition, inpatient (IP) charges, and ED charges were calculated. During the period between 2006 and 2019, 15841 ED encounters had RT listed as the primary diagnosis. The average annual RT ED encounters was 2,640 ± 856 and comprised an average of 6.4 × 10−5% of all ED visits annually. The number and ED percentage of RT encounters did not change during this time period (p = .22, p = .67, respectively). Most patients were males, Caucasian, paid with private insurance, and admitted to EDs in the Northeast. The most common comorbidities were hypertension (19%), a history of cataracts (15%), and diabetes (7.2%). During this time period, RTs charges added up to more than $79 million and $33 million in the ED and IP settings, respectively. Mean per-encounter ED and IP charges increased by 145% (p = .0008) and 86% (p = .0047), respectively. Despite the stable number of RT patients presenting to the ED, RTs place a significant economic burden to the healthcare system, which increases yearly. We recommend physicians and policy makers to work together to pass laws that could prevent the increasing healthcare charges.

This paper describes the system architectures and the models submitted by our team "IISERBBrains" to SemEval 2022 Task 6 competition. We contested for all three sub-tasks floated for the English dataset. On the leader-board, wegot19th rank out of43 teams for sub-taskA, the 8th rank out of22 teams for sub-task B,and13th rank out of 16 teams for sub-taskC. Apart from the submitted results and models, we also report the other models and results that we obtained through our experiments after organizers published the gold labels of their evaluation data, Comment: 7 pages

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two inputs and require the output to be invariant of the order of the inputs, inconsistency is often observed in the predicted labels or confidence scores. We highlight this model shortcoming and apply a consistency loss function to alleviate inconsistency in symmetric classification. Our results show an improved consistency in predictions for three paraphrase detection datasets without a significant drop in the accuracy scores. We examine the classification performance of six datasets (both symmetric and non-symmetric) to showcase the strengths and limitations of our approach., Comment: 9 pages, 2 figures, ACL Findings 2022

Supplemental material, sj-pdf-1-pul-10.1177_2045894021996224 for Outcomes of patients hospitalized for acute pulmonary embolism by obstructive sleep apnea status by Aditya A. Joshi, Raef H. Hajjali, Avantee V. Gokhale, Triston Smith, Amit K. Dey, Garima Dahiya, Joseph B. Lerman, Aparna P. Sajja, Manreet Kanwar and Amresh Raina in Pulmonary Circulation

Supplemental material, sj-pdf-1-pul-10.1177_2045894021996224 for Outcomes of patients hospitalized for acute pulmonary embolism by obstructive sleep apnea status by Aditya A. Joshi, Raef H. Hajjali, Avantee V. Gokhale, Triston Smith, Amit K. Dey, Garima Dahiya, Joseph B. Lerman, Aparna P. Sajja, Manreet Kanwar and Amresh Raina in Pulmonary Circulation

Additional file1: Supplementary data of Control Sample, acid degradation, Base degradation, peroxide degradation and sample preparation under specificity are mentioned as figures indicating SF-1 to 5. Supplementary data of results of linearity, results of specificity and results of Precision are mentioned as Table indicating ST-1 to 3.

Cross-domain sentiment analysis (CDSA) helps to address the problem of data scarcity in scenarios where labelled data for a domain (known as the target domain) is unavailable or insufficient. However, the decision to choose a domain (known as the source domain) to leverage from is, at best, intuitive. In this paper, we investigate text similarity metrics to facilitate source domain selection for CDSA. We report results on 20 domains (all possible pairs) using 11 similarity metrics. Specifically, we compare CDSA performance with these metrics for different domain-pairs to enable the selection of a suitable source domain, given a target domain. These metrics include two novel metrics for evaluating domain adaptability to help source domain selection of labelled data and utilize word and sentence-based embeddings as metrics for unlabelled data. The goal of our experiments is a recommendation chart that gives the K best source domains for CDSA for a given target domain. We show that the best K source domains returned by our similarity metrics have a precision of over 50%, for varying values of K., Comment: 12th Edition of Language Resources and Evaluation Conference (LREC 2020)

Epidemic intelligence deals with the detection of disease outbreaks using formal (such as hospital records) and informal sources (such as user-generated text on the web) of information. In this survey, we discuss approaches for epidemic intelligence that use textual datasets, referring to it as `text-based epidemic intelligence'. We view past work in terms of two broad categories: health mention classification (selecting relevant text from a large volume) and health event detection (predicting epidemic events from a collection of relevant text). The focus of our discussion is the underlying computational linguistic techniques in the two categories. The survey also provides details of the state-of-the-art in annotation techniques, resources and evaluation strategies for epidemic intelligence., Comment: This paper is under review at ACM Computing Surveys. This version of the paper does not use the ACM Computing Surveys stylesheet. This arXiv version is to solicit feedback

This study hypothesized that there is an association between chronic stress (as indexed by resting amygdalar activity [AmygA]), hematopoietic system activity (HMPA), and subclinical cardiovascular indexes (aortic vascular inflammation [VI] and noncalcified coronary plaque burden [NCB]) in psoriasis (PSO). The study also hypothesized that treatment of PSO would improve these parameters.PSO is a stress-related chronic inflammatory condition that is associated with increased prevalence of subclinical cardiovascular disease (CVD). In individuals without PSO, stress has been linked to CVD through a serial biological pathway that involves the amygdala, hematopoietic tissues, and atherosclerotic plaques.A total of 164 consecutive patients with PSO and 47 healthy volunteers underwent 18-fluorodeoxyglucose positron emission tomography/computed tomography scans for assessment of AmygA, HMPA, and VI, as well as coronary computed tomography angiography scans for quantifying NCB. Furthermore, a consecutive subset of 30 patients with severe PSO (Psoriasis Area Severity Index Score10) were followed at 1 year to assess the relationship between skin disease improvement and AmygA, HMPA, VI, and NCB.The PSO cohort was middle-aged (mean age: 50 years), had low cardiovascular risk (Framingham risk score: median: 3) and had mild to moderate PSO activity (median Psoriasis Area Severity Index Score: 5.6). AmygA was higher in patients with PSO compared to volunteer participants. AmygA was associated with HMPA (bone marrow activity: β = 0.20, p = 0.01) and subclinical CVD (VI: β = 0.31, p 0.001; NCB: β = 0.27, p 0.001) The AmygA-CVD association was in part mediated by HMPA (VI: 20.9%, NCB: 36.7%). Following 1 year of PSO treatment in those with severe disease, improvement in skin disease was accompanied by a reduction in AmygA, bone marrow activity, and VI, with no progression of NCB.In PSO, a chronic inflammatory disease state, AmygA, which is a manifestation of chronic stress, substantially contributes to the risk of subclinical CVD. Additional studies that use psychometric measures of stress are required to explore therapeutic impact.

This paper reports an increment to the state-of-the-art in hate speech detection for English-Hindi code-mixed tweets. We compare three typical deep learning models using domain-specific embeddings. On experimenting with a benchmark dataset of English-Hindi code-mixed tweets, we observe that using domain-specific embeddings results in an improved representation of target groups, and an improved F-score., Comment: This paper will appear at the 15th International Conference on Natural Language Processing (ICON-2018) in India in December 2018. ICON is a premier NLP conference in India

Sarcasm is verbal irony that is intended to mock or ridicule. Existing sentiment analysis systems show a degraded performance in case of sarcastic text. Hence, computational sarcasm has received attention from the sentiment analysis community. Computational sarcasm refers to computational techniques that deal with sarcastic text. This thesis presents our investigations in computational sarcasm based on the linguistic notion of incongruity. For example, the sentence `I love being ignored' is sarcastic because the positive word `love' is incongruous with the negative phrase `being ignored'. These investigations are divided into three parts: understanding the phenomenon of sarcasm, sarcasm detection and sarcasm generation. To first understand the phenomenon of sarcasm, we consider two components of sarcasm: implied negative sentiment, and presence of a target. To understand how implied negative sentiment plays a role in sarcasm understanding, we present an annotation study which evaluates the quality of a sarcasm-labeled dataset created by non-native annotators. Following this, in order to show how the target of sarcasm is important to understand sarcasm, we first describe an annotation study which highlights the challenges in distinguishing between sarcasm and irony (since irony does not have a target while sarcasm does), and then present a computational approach that extracts the target of a sarcastic text. We then present our approaches for sarcasm detection. To detect sarcasm, we capture incongruity in two ways: `intra-textual incongruity' where we look at the incongruity within the text to be classified (i.e., target text), and the `context incongruity' where we incorporate information outside the target text. To detect incongruity within the target text, we present four approaches: (a) A classifier that captures sentiment incongruity using sentiment-based features (as in the case of `I love being ignored'), (b) A classifier that captures semantic incongruity (as in the case of `A woman needs a man like a fish needs bicycle') using word embedding-based features, (c) A topic model that captures sentiment incongruity using sentiment distributions in the text (in order to discover sarcasm-prevalent topics such as work, college, etc.), and (d) An approach that captures incongruity in the language model using sentence completion. The approaches in (a) and (c) incorporate sentiment incongruity relying on sentiment-bearing words, whereas approach in (b) and (d) tackle other forms of incongruity where sentiment-bearing words may not be present. On the other hand, to detect sarcasm using contextual incongruity, we describe two approaches: (a) A rule-based approach that uses historical text by an author to detect sarcasm in the text generated by them, and (b) A statistical approach that uses sequence labeling techniques for sarcasm detection in dialogue. The approach in (a) attempts to detect sarcasm that requires author-specific context while that in (b) attempts to detect sarcasm that requires conversation-specific context. Finally, we present an technique for sarcasm generation. In this case, we use a template-based approach to synthesize incongruity and generate a sarcastic response to user input. Our investigations demonstrate how evidences of incongruity (such as sentiment incongruity, semantic incongruity, etc.) can be modeled using different learning techniques (such as classifiers, topic models, etc.) for sarcasm detection and sarcasm generation. In addition, our findings establish the promise of novel problems like sarcasm target identification and sarcasm versus irony classification, and provide insights for future research in sarcasm detection.

The trigram `I love being' is expected to be followed by positive words such as `happy'. In a sarcastic sentence, however, the word `ignored' may be observed. The expected and the observed words are, thus, incongruous. We model sarcasm detection as the task of detecting incongruity between an observed and an expected word. In order to obtain the expected word, we use Context2Vec, a sentence completion library based on Bidirectional LSTM. However, since the exact word where such an incongruity occurs may not be known in advance, we present two approaches: an All-words approach (which consults sentence completion for every content word) and an Incongruous words-only approach (which consults sentence completion for the 50% most incongruous content words). The approaches outperform reported values for tweets but not for discussion forum posts. This is likely to be because of redundant consultation of sentence completion for discussion forum posts. Therefore, we consider an oracle case where the exact incongruous word is manually labeled in a corpus reported in past work. In this case, the performance is higher than the all-words approach. This sets up the promise for using sentence completion for sarcasm detection., Comment: 6 pages, The paper will be presented at PACLING 2017 as an oral presentation. A note saying so has been added to the beginning of this paper

Past work in computational sarcasm deals primarily with sarcasm detection. In this paper, we introduce a novel, related problem: sarcasm target identification i.e., extracting the target of ridicule in a sarcastic sentence). We present an introductory approach for sarcasm target identification. Our approach employs two types of extractors: one based on rules, and another consisting of a statistical classifier. To compare our approach, we use two baselines: a na\"ive baseline and another baseline based on work in sentiment target identification. We perform our experiments on book snippets and tweets, and show that our hybrid approach performs better than the two baselines and also, in comparison with using the two extractors individually. Our introductory approach establishes the viability of sarcasm target identification, and will serve as a baseline for future work.

Alcohol abuse may lead to unsociable behavior such as crime, drunk driving, or privacy leaks. We introduce automatic drunk-texting prediction as the task of identifying whether a text was written when under the influence of alcohol. We experiment with tweets labeled using hashtags as distant supervision. Our classifiers use a set of N-gram and stylistic features to detect drunk tweets. Our observations present the first quantitative evidence that text contains signals that can be exploited to detect drunk-texting., Comment: This paper was presented at ACL-IJCNLP 2015

Topic Models have been reported to be beneficial for aspect-based sentiment analysis. This paper reports a simple topic model for sarcasm detection, a first, to the best of our knowledge. Designed on the basis of the intuition that sarcastic tweets are likely to have a mixture of words of both sentiments as against tweets with literal sentiment (either positive or negative), our hierarchical topic model discovers sarcasm-prevalent topics and topic-level sentiment. Using a dataset of tweets labeled using hashtags, the model estimates topic-level, and sentiment-level distributions. Our evaluation shows that topics such as `work', `gun laws', `weather' are sarcasm-prevalent topics. Our model is also able to discover the mixture of sentiment-bearing words that exist in a text of a given sentiment-related label. Finally, we apply our model to predict sarcasm in tweets. We outperform two prior work based on statistical classifiers with specific features, by around 25\%., Comment: This version of the paper contains corrected changes, after the camera -ready submission. These changes were observed based on an issue in the output returned by SVM Perf. This paper will be presented at ExPROM workshop at COLING 2016