Soumya Sharma

The NorthCap University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Niloy Ganguly

Indian Institute of Technology Kharagpur

Koustuv Dasgupta

Xerox (France)

Pawan Goyal

Indian Institute of Technology Kharagpur

Tapas R. Nayak

Proteogenomics Research Institute for Systems Medicine

Srishti Sharma

All India Institute of Medical Sciences Rishikesh

Ajay Kumar Meena

Central Council for Research in Ayurvedic Science

Arusarka Bose

Indian Institute of Technology Kharagpur

Trupti Lotlikar

Terna Dental College and Hospital

Abhinav Bohra

Indian Institute of Technology Kharagpur

Deepak Gupta

Guru Gobind Singh Indraprastha University

Cooperative Institutions

Indian Institute of Technology Kharagpur

Lovely Professional University

Indian Institute of Engineering Science and Technology, Shibpur

Guru Gobind Singh Indraprastha University

University of Mumbai

Leibniz University Hannover

Indian Institute of Technology Indore

Samsung (United Kingdom)

Max Planck Society

ITM University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

An analysis of brand loyalty towards fashion and apparel

International Journal of Research in Marketing Management and Sales (2021)

Lalit Bhardwaj Soumya Sharma Amanjot Kaur Pabla Shivam Raikwar Raghav Khandelwal

Competition amongst firms is intense within the fashion industry, with more options for the consumer than ever before. Firms are altering their brand strategies to adopt and manage this increase in competition with an apparent increase in effort to form a connection between brand and consumer. Cultivating a brand loyalty is more important than ever for fashion firms, to ensure that their brand has a stable sales basis and a positive image. There is a suggestion however that loyalty may be dissipating. With the emergence of fast-fashion brands who offer similar styles to more expensive brands but at a more affordable prices, it be deemed that it is no longer enough to offer just a high-quality product but to offer intangible benefits to the consumer such as an identification with the brands personality. This dissertation attempts to understand the reasons for brand loyalty or lack of brand loyalty amongst millennial consumers in this sector. Millennial are frequent consumers of clothing products, therefore attempting to understand their consumption activities are of real benefit to fashion firms. The objective of this research is to identify the key brand characteristics which can spark brand loyalty. An online survey was utilized to collect both quantitative and qualitative data from 200 respondents in the millennial age bracket in a mixed method approach.

Brand Loyalty

10.33545/26633329.2021.v3.i1a.63

Cite

Citations (1)

ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcripts

arXiv (Cornell University) (2022)

Rajdeep Mukherjee Abhinav Bohra Akash Banerjee Soumya Sharma M.V. Hegde

Despite tremendous progress in automatic summarization, state-of-the-art methods are predominantly trained to excel in summarizing short newswire articles, or documents with strong layout biases such as scientific articles or government reports. Efficient techniques to summarize financial documents, including facts and figures, have largely been unexplored, majorly due to the unavailability of suitable datasets. In this work, we present ECTSum, a new dataset with transcripts of earnings calls (ECTs), hosted by publicly traded companies, as documents, and short experts-written telegram-style bullet point summaries derived from corresponding Reuters articles. ECTs are long unstructured documents without any prescribed length limit or format. We benchmark our dataset with state-of-the-art summarizers across various metrics evaluating the content quality and factual consistency of the generated summaries. Finally, we present a simple-yet-effective approach, ECT-BPS, to generate a set of bullet points that precisely capture the important facts discussed in the calls.

Benchmark (surveying)

Unavailability

10.48550/arxiv.2210.12467

Cite

Citations (0)

FinRED: A Dataset for Relation Extraction in Financial Domain

arXiv (Cornell University) (2023)

Soumya Sharma Tapas R. Nayak Arusarka Bose Ajay Kumar Meena Koustuv Dasgupta

Relation extraction models trained on a source domain cannot be applied on a different target domain due to the mismatch between relation sets. In the current literature, there is no extensive open-source relation extraction dataset specific to the finance domain. In this paper, we release FinRED, a relation extraction dataset curated from financial news and earning call transcripts containing relations from the finance domain. FinRED has been created by mapping Wikidata triplets using distance supervision method. We manually annotate the test data to ensure proper evaluation. We also experiment with various state-of-the-art relation extraction models on this dataset to create the benchmark. We see a significant drop in their performance on FinRED compared to the general relation extraction datasets which tells that we need better models for financial relation extraction.

Relationship extraction

Benchmark (surveying)

Open domain

10.48550/arxiv.2306.03736

Cite

Citations (0)

Design and Development of Sensor in Measuring Force

International Journal for Research in Applied Science and Engineering Technology (2022)

Shaikh Khalid Mudassir Khan Soumya Sharma Suyog Parkhe

Abstract: In this project, we are going to measure the force applied by a headphone on a human ear. For this, we are using FSR (Force Sensitive Resistor) to measure the force. The FSR is interfaced with Arduino Uno for the required purpose along with a 10 km ohm resistor (pull down resistor). The resistance offered is a sum of two resistances means FSR resistance + pull down resistor's resistance which fluctuates between 100 Kohm to 10 Kohm . Also a LCD display connected with a variable 10 Kohm resistor is used to display the force value in Newton. We have taken 2 readings of each different headset one is the maximum value observed and second is the minimum value observed. A mean is taken of these two values and an overall mean of all values of different headsets is taken. Hence the value got, is an average suitable value that a headphone should apply on human ears so that they can be worn for a longer period of time. (approx 4 to 5 hours) Keywords: Force Resistive Sensors, Arduino Nano, Force Measurement.

Resistive touchscreen

Arduino

Value (mathematics)

Mean value

Headset

10.22214/ijraset.2022.40734

Cite

Citations (0)

Multimodal Sentiment Analysis and Multimodal Emotion Analysis: A Review

Lecture notes in networks and systems (2024)

Soumya Sharma Srishti Sharma Deepak Gupta

Multimodal therapy

Sentiment Analysis

Multimodality

10.1007/978-981-97-0892-5_29

Cite

Citations (0)

INTERNATIONAL JOURNA L OF ENGINEERING SCI ENCES & RESEARCH TECHNOLOGY Augmented Reality -An Emerging Technology

Trupti Lotlikar Divya Mahajan Javid Khan Ritvik Ranadive Soumya Sharma

Augmented reality (AR) is the view of a physical, r eal -world environment that is live, direct or indirect and whose elements are augmented by computer -generated sensory input such as sound, video, graph ics or GPS data. In of Augmented Reality as well as the various implementation techniques available in the field of Augmented Reality. Augmentation is conventionally in real -time and in semantic context with environmental elements, such as sports scores on TV during a match. With the help of advanced AR technology (e.g. adding computer vision and object recognition ) the information about the surrounding real world of the user becomes interactive and digitally manipulable. The general principle of the augmented reality (AR) is digital information into the real world scene. Thus it is a step between virtual reality and the real world. world environment, augmentation, virtual reality.

Artificial reality

Source

Cite

Citations (0)

Unveiling Emotions in the Digital Arena: Sentiment Analysis of YouTube Comments on FIFA World Cup 2022

Soumya Sharma Srishti Sharma Deepak Gupta

YouTube is a popular video sharing website and a social networking platform where users can upload (only registered users), watch and share videos on any particular topic with anyone who can access the site and also share their views about the video in the comment section. Since the YouTube comment section has no word/character limit, the users/viewers can easily express their thoughts and viewpoint in great detail. Also, in the comment section, the users make use of all kinds of emoticons, abbreviations, images, GIFs, etc. In this paper, we deploy different machine learning algorithm along with the Tf-IDF (term frequency- inverse document frequency) method on the comments collected from various YouTube videos on the FIFA World Cup 2022 and compute an accuracy of 81.81% with Random Foresta and 83.03% with Logistic Regression

Upload

Section (typography)

Sentiment Analysis