Department of Computer Science and Information Systems

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1928

Browse

Filters

2018 - 201922020 - 20238

Settings

Author: search.filters.author.Sharma, YashvardhanSubject: search.filters.subject.Deep Learning (DL)

Search Results

Now showing 1 - 10 of 10
  • No Thumbnail Available
    Item
    Composite Sequential Modeling for Identifying Fake Reviews
    (De Gruyter, 2018-04) Sharma, Yashvardhan
    This paper presents a comprehensive analysis and comparison of various proposed sequential models based on different deep networks such as the convolutional neural network, long short-term memory, and recurrent neural network. The different sequential models are analyzed based on the number of layers, the number of output dimensions, order, and the combination of different deep network architectures. The proposed approach is compared to a baseline model based on traditional machine learning techniques.
  • No Thumbnail Available
    Item
    Neural Network-Based Architecture for Sentiment Analysis in Indian Languages
    (De Gruyter, 2018-06) Sharma, Yashvardhan
    Sentiment analysis refers to determining the polarity of the opinions represented by text. The paper proposes an approach to determine the sentiments of tweets in one of the Indian languages (Hindi, Bengali, and Tamil). Thirty-nine sequential models have been created using three different neural network layers [recurrent neural networks (RNNs), long short-term memory (LSTM), convolutional neural network (CNN)] with optimum parameter settings (to avoid over-fitting and error accumulation). These sequential models have been investigated for each of the three languages. The proposed sequential models are experimented to identify how the hidden layers affect the overall performance of the approach. A comparison has also been performed with existing approaches to find out if neural networks have an added advantage over traditional machine learning techniques.
  • No Thumbnail Available
    Item
    Deep Extractive Text Summarization
    (Elsevier, 2020) Sharma, Yashvardhan
    With introduction of deep learning techniques their has been an increase in intelligent classification of text in many applications. Advances in automatic text summarization using deep learning technique is prime focus of research now a days. Earlier traditional approaches for extractive text summarization have been heavily dependent on human engineered features. However, it is a laborious and tedious task. In this paper, a data-driven approach has been used to generate extractive summaries using deep learning. Approach proposed uses paraphrasing techniques to classify sentences as a candidate sentence for inclusion in summary or not.
  • No Thumbnail Available
    Item
    Deep Text Summarization using Generative Adversarial Networks in Indian Languagess
    (Elsevier, 2020) Sharma, Yashvardhan
    Abstractive Text Summarization (ATS) is a task of capturing information from different sources and condense it such that, content is represented well and there is no loss of information. It has been an active area of research for quiet sometime now. ATS is more closer to human generated summaries and have the capability of representing and combining multiple information. With advent of deep learning architectures, many tasks relating to natural language processing have achieved persistent and comparable high performances. It has proven advantageous and showed promising results in machine translation, speech recognition, image captioning and many others using sequence to sequence models. Language tools such as Part of Speech taggers, Named Entity Recognizer for Indian languages are not very competitive and hence, language specific techniques do not perform very well for Indian languages. Deep learning techniques are language agnostic and hence can overcome these shortcomings. In this paper, Generative Adversarial Networks(GAN(s)) are assimilated to create gist for longer piece of text in conjunction to paraphrase detection.
  • No Thumbnail Available
    Item
    Detection of Threat Records by Analyzing the Tweets in Urdu Language Exploring Deep Learning Transformer - Based Models
    (CEUR-WS, 2021) Sharma, Yashvardhan
    As humans, we express sadness, anger, happiness, frustration, bullying, etc., in both physical and virtual worlds. In the virtual world, i.e., social media, we use textual ways to express ourselves. Due to the lack of offensive and threatening language detection mechanisms aggressive behavior in social media is not always followed by an immediate consequence. But the impact of these posts on the victim can cause prolonged mental illness and instigate fear for social media platforms. This paper aims to identify threatening posts using deep learning transformer-based models such as Roberta. The Urdu tweet dataset used in this study has been provided by HASOC-2021 which aims to identify Hate speech and offensive remarks without human assistance. We submitted our model in its subtask B of the 4th subtrack(Abusive and Threatening language detection in Urdu), secured 2nd position on the public leaderboard, and obtained Weighted f1 of 0.5346 and ROC AUC of 0. 8199.
  • No Thumbnail Available
    Item
    Comparative Analysis of Various Machine Learning Based Techniques for Predicting the Virality of Tweets
    (IEEE, 2022) Sharma, Yashvardhan
    Social media has become more popular, and people tend to read the news more often from it than traditional media. But all the information that is posted on the social media platform might not go viral. In this paper, we have analyzed the data from one of the social media platforms, Twitter, and established a few reasons for the virality of tweets. Along with it, given the tweet information and user details to the trained model, we could predict whether the tweets go viral or not. For this, we used multiple architectures from classical machine learning like Random Forest, XGBoost and Lightgbm and Convolutions from Deep Learning and got the highest accuracy using the Lightgbm model. The results show that using both text and image data combined provides better results when compared with using only text or images (unimodal data). The data used is from the competition with full user details, tweet information, and tweet text and image.
  • No Thumbnail Available
    Item
    Domain-Specific Chatbot Development Using the Deep Learning-Based RASA Framework
    (Springer, 2022-08) Sharma, Yashvardhan
    Conversational agents are actively gaining popularity in research because of their ability to imitate human responses in almost every domain. As there are many research enhancements in deep learning models, it becomes challenging to incorporate all these enhancements while developing a conversational agent. One of the main advantages of conversational agents is their ability to answer frequently asked queries without any human involvement and automatically generate the conversation’s story flow. In any educational institution, it becomes difficult for the teaching and non-teaching staff to answer all the students’ queries regarding the course, exam, and other information regarding their daily activities in the institute. Using the deep learning framework, we developed a chatbot to answer various questions related to the education domain, such as exam(timetable, venue) and course-related queries(course handout). The questions are answered by querying databases which can be updated via an administrator’s web browser. The system will first create intents for the use cases and entity recognition mechanisms after connecting the deep learning framework to the database using custom actions. We had created a user interface to allow updates to the database for exam timetable and course information via either file upload or a web page.
  • No Thumbnail Available
    Item
    FakeRevealer: A Multimodal Framework for Revealing the Falsity of Online Tweets Using Transformer-Based Architectures
    (Scitepress, 2023) Sharma, Yashvardhan; Chauhan, Gajendra Singh
    As the Internet has evolved, the exposure and widespread adoption of social media concepts have altered the way news is formed and published. With the help of social media, getting news is cheaper, faster, and easier. However, this has also led to an increase in the number of fake news articles, either by manipulating the text or morphing the images. The spread of fake news has become a serious issue all over the world. In one case, at least 20 people were killed just because of false information that was circulated over a social media platform. This makes it clear that social media sites need a system that uses more than one method to spot fake news stories. To solve this problem, we’ve come up with FakeRevealer, a single-configuration fake news detection system that works on transfer learning based techniques. Our multi-modal archutecture understands the textual features using a language transformer model called DistilRoBERTa and image features are extracted using the Vision Transf ormer (ViTs) that is pre-trained on ImageNet 21K. After feature extraction, a cosine similarity measure is used to fuse both the features. The evaluation of our proposed framework is done over publicly available twitter dataset and results shows that it outperforms current state-of-art on twitter dataset with an accuracy of 80.00% which is 2.23%more, that than the current state-of-art on twitter dataset
  • No Thumbnail Available
    Item
    ArabiziVec: A Set of ArabiziWord Embeddings for Informal Arabic Sentiment Analysis
    (Sentic, 2023) Sharma, Yashvardhan
    The current circumstances of the Arab world have provided bloggers and commenters with various subjects to discuss. Therefore, Arabic-generated content in social media is ramping up continuously. An informal written form of spoken Arabic called Arabizi has recently emerged as a commonly used language in the Arabic space, attracting great interest for sentiment analysis tasks. However, only a few sentiment resources exist, and state-of-the-art language models such as BERT and FastText do not consider Arabizi yet. This paper presents the first version of ArabiziVec, a set of pre-trained distributed word representations. ArabiziVec provides six different word embedding models to deal with Arabizi sentiment analysis challenges. The presented work surpasses all of the baseline sets for each experiment, regardless of whether the test set is from a previously published dataset or an extracted one. To the best of our knowledge, this is one of the first few resources that deals with Arabizi content and semantics in the context of sentiment analysis
  • No Thumbnail Available
    Item
    Scalability and Sustainability in Chatbot and Mobile Application Development
    (IEEE, 2023) Sharma, Yashvardhan
    A primary concern in the development of mobile applications is ensuring that the apps can manage a rising user base without degrading the user experience or performance. Therefore, the application’s architecture needs to be able to handle several requests per minute. Considering the scalability aspect, we developed a multilingual Chatbot using RASA as the Natural Language Processing (NLP) library, flutter as the cross-platform application development framework, and Django framework for doing server-side manipulations. Our application showcases the best architectural and security practices in application development to make the model scalable over time and keep it free from any security threats. The entire work is divided into two main components: a mobile application for the chatbot and a desktop website where users can enter data in several languages to train a deep learning-based model for intent detection. The developed chatbot, designed to be a university bot, will automatically identify the user’s preferred language and provide responses in that language. We aimed to make the application user-friendly and as safe as possible.