Search

Customers are rapidly turning to social media for customer support. While brand agents on these platforms are motivated and well-intentioned to help and engage with customers, their efforts are often ignored if their initial response to the customer does not match a specific tone, style, or topic the customer is aiming to receive. The length of a conversation can reflect the effort and quality of the initial response made by a brand toward collaborating and helping consumers, even when the overall sentiment of the conversation might not be very positive. Thus, through this study, we aim to bridge this critical gap in the existing literature by analyzing language's content and stylistic aspects such as expressed empathy, psycho-linguistic features, dialogue tags, and metrics for quantifying personalization of the utterances that can influence the engagement of an interaction. This paper demonstrates that we can predict engagement using initial customer and brand posts., Comment: Accepted to NLP+CSS at EMNLP 2022

Ritu Arora,1 Ruchi Goel,1 Samreen Khanam,1 Sumit Kumar,1 Shalin Shah,1 Sonam Singh,1 Mohit Chhabra,1 Ravi Meher,2 Nita Khurana,3 Tanu Sagar,4 Suresh Kumar,5 Sandeep Garg,5 Jyoti Kumar,6 Sonal Saxena,4 Rashmi Pant7 1Department of Ophthalmology, Guru Nanak Eye Centre, Maulana Azad Medical College, New Delhi, India; 2Department of Otorhinolaryngology, Maulana Azad Medical College, New Delhi, India; 3Department of Pathology, Maulana Azad Medical College, New Delhi, India; 4Department of Microbiology, Maulana Azad Medical College, New Delhi, India; 5Department of Medicine, Maulana Azad Medical College and Lok Nayak Hospital, New Delhi, India; 6Department of Radiodiagnosis, Maulana Azad Medical College and Lok Nayak Hospital, New Delhi, India; 7Society for Health Education and Allied Research, New Delhi, IndiaCorrespondence: Ruchi GoelDepartment of Ophthalmology, Guru Nanak Eye Centre, Maulana Azad Medical College, New Delhi, 110002, IndiaTel +91 9811305645; +91-11-41440108Email gruchi1@rediffmail.comPurpose: To list the clinico-epidemiological profile and possible risk factors of COVID-19 associated rhino-orbital-cerebral mucormycosis (CA-ROCM) patients presenting to a COVID dedicated hospital during the second wave of COVID-19 in India.Patients and Methods: A cross-sectional, single-center study was done on 60 cases of probable CA-ROCM based on clinical features and supportive diagnostic nasal endoscopic findings and/or radiologic findings. Patients with recent or active COVID-19 were included. The demographic profile, clinical features, possible risk factors and diagnostic workup (microbiological, pathological and radiological) were analysed to identify the triggering factors for CA-ROCM.Results: The age of patients ranged from 29 to 75 years and male–female ratio was 3:1. The duration between the first positive COVID report and onset of CA-ROCM was 0 to 47 days. Forty-nine (81.66%) patients had a recent COVID infection and 11 (18.33%) had active COVID infection at p

India is one of the leading countries in agricultural production and generate large volume of crop residue. Increasing demand for food grains due to growing population leads to generation of crop residues. Due to lack of proper disposal mechanism of crop residue, farmers burn the residue which release greenhouse gases (GHGs) into the atmosphere, and poses great threat to environment as well as human health. The residue burning causes greater carbon emission and nutrient losses which otherwise incorporated into the soil system may substantially improve the soil biodiversity. Besides several practices of crop residue management, the most feasible method for farmers is incorporation of residue into the soil with the inoculation of microbes. In soil system the ability of microbial community in degrading organic substances is well known. In the early stages of residue decomposition simple substrates like carbohydrates are degraded by bacteria, but in later stages degradation of complex constituents viz., cellulose, lignin needs microbes which are capable of secreting enzymes like cellulase, acting on complex organic substrates. In this context, cellulolytic micro organisms like Trichoderma have the potential and emerging as an important microbial inoculants to enhance the rate of decomposition as well as alleviate the effect of residue burning.

Automatic segmentation of retinal blood vessels from fundus images plays an important role in the computer aided diagnosis of retinal diseases. The task of blood vessel segmentation is challenging due to the extreme variations in morphology of the vessels against noisy background. In this paper, we formulate the segmentation task as a multi-label inference task and utilize the implicit advantages of the combination of convolutional neural networks and structured prediction. Our proposed convolutional neural network based model achieves strong performance and significantly outperforms the state-of-the-art for automatic retinal blood vessel segmentation on DRIVE dataset with 95.33% accuracy and 0.974 AUC score.