DDDheeraj Kumar Dixit

Dheeraj Kumar Dixit

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dheeraj Kumar Dixit has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Performance Comparison of Static and Contextual Embedding Models for Opinion Mining

    by Dharmendra Dangi, Abhay Sharma, Dheeraj Kumar Dixit, Amit Bhagat, Chandrapal Singh Dangi

    Transformer-based language models are widely adopted for sentiment analysis due to their strong contextual representation capabilities; however, their high computational complexity can limit practical deployment in resource-constrained environments. This work presents a systematic comparative study of static and contextual word representations for sentiment classification across architecturally distinct model families under standardized preprocessing and evaluation conditions. We evaluate Long Short-Term Memory (LSTM) networks with Word2Vec, GloVe, and FastText embeddings, and compare them with fine-tuned BERT-base and DistilBERT transformer baselines using the same preprocessing, training, and evaluation protocols across five publicly available datasets spanning formal reviews and noisy social media text. In addition to overall accuracy, we report macro- and weighted-F1 scores across three random seeds to estimate experimental variance, and apply McNemar’s test (with Bonferroni correction for multiple comparisons) to assess pairwise model differences on each dataset’s test set. Contingency tables required for each McNemar comparison are provided in the supplementary material. Detailed error analyses using confusion matrices and out-of-vocabulary (OOV) statistics examine the impact of lexical coverage on model performance. Experimental results indicate that FastText consistently outperforms other static embeddings, particularly on datasets with high lexical variability, while offering substantially lower computational overhead compared to the transformer baselines. The primary contribution of this study is a diagnostic multi-dataset evaluation framework that quantifies the relationship between lexical coverage and subword modeling benefit, and characterises the efficiency–accuracy trade-off across embedding paradigms. All architectural and training differences between model families are explicitly documented and their confounding effects discussed rather than assumed away. These findings provide practical guidance for selecting embedding strategies by jointly considering accuracy and deployment efficiency.

  • Multilingual AI-Generated Text Detection with BERT and LSTM Model

    by Jeetendra Kumar, Rashmi Gupta, Suvarna Sharma, Jatin Arora, Dharmendra Dangi, Dheeraj Kumar Dixit

    The advent of AI-generated text, driven by advanced language models like GPT (Generative Pre-trained Transformer) and BERT (Bidirectional Encoder Representations from Transformers) has revolutionized content creation but also raised concerns about authenticity and misuse in various domains. This research proposes a system to detect whether the supplied text is written by human-being or it generated by AI algorithms, supporting both English and Hindi languages using two datasets with mixed human-authored and AI-generated content. After pre-processing steps such as tokenization, cleaning, and normalization, trained the models including BERT, LSTM (Long Short Term Memory), Logistic Regression, SVM (Support Vector Machine), Random Forest, and Naive Bayes, with BERT finetuned for contextual understanding and LSTM for sequential data, achieving higher accuracy in both languages. A userfriendly interface was developed to allow text file uploads for instant authenticity predictions, serving academic, journalistic, and digital media contexts, with the study highlighting transformer-based models' potential in multilingual detection to enhance digital content trustworthiness and mitigate AIgenerated text misuse. Using the proposed method, accuracies of 95.76 % in English text and 95.58 % in Hindi text have been obtained. The proposed system was found to be effective in detecting text generated by AI algorithms.

  • Utilization of hesitant and intuitionistic fuzzy sets (HFS-IFS) in computational intelligence for decision modeling

    by Suvarna Sharma, Dharmendra Dangi, Dheeraj Kumar Dixit, Rashmi Gupta, Jeetendra Kumar, Amit Bhagat


  • Efficient Deep Learning Model for Analyzing Muscle Activity Patterns in Biomechanical Simulations

    by Dharmendra Dangi, Dheeraj Kumar Dixit, Amit Bhagat, Durgesh Rao, Jeetendra Kumar Gupta


  • Open Access

    A comparative analysis for detecting fake news using supervised learning algorithms

    by Dheeraj Kumar Dixit, Amit Bhagat, Dharmendra Dangi

    Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the soci Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the soci


  • An accurate fake news detection approach based on a Levy flight honey badger optimized convolutional neural network model

    by Dheeraj Kumar Dixit, Amit Bhagat, Dharmendra Dangi

    Summary: People can quickly acquire the news through a variety of sources, including websites, blogs, and social media, among others. The spread of fake news has become easier as a result of the availability of these platforms. Anybody with access to these networks generates and distributes fake news for professional or personal gain. Numerous studies relying on supervised and unsupervised learning techniques are available to address the issue of recognizing fake news. All of those studies, though, have one flaw: they all deliver mostly inaccurate or unmatched results. Poor accuracy is attributed to a variety of factors, including imbalanced datasets, inefficient parameter tuning, poor feature selection, and so on. To tackle these issues, we proposed a novel approach for fake news detection. Initially, the data were obtained from the ISOT dataset and data cleaning is performed. After that, preprocessing is done which includes three major steps such as stemming, stop word removal, and tokenization are carried out. Next to preprocessing, various features that involve name entity recognition‐based features are selected during feature extraction. From this, the short dimensionality features are selected with the help of the ensemble modified independent component analysis model. Finally, the hybrid convolutional neural network‐based Levy flight‐based honey badger algorithm detects fake news. The experiments are simulated using python software with various performance metrics such as accuracy, specificity, sensitivity, precision, and F‐scores to validate the performance of the proposed method. The proposed model offers a precision, recall, and accuracy value of 95%, 97%, and 98% when evaluated with the ISOT dataset. When compared to the existing state‐of‐art methods, the proposed method yielded superior detection results and higher accuracy rates.


  • Automating fake news detection using PPCA and levy flight-based LSTM

    by Dheeraj Kumar Dixit, Amit Bhagat, Dharmendra Dangi

    In recent years, rumours and fake news are spreading widely and very rapidly all over the world. Such circumstances lead to the propagation and production of an inaccurate news article. Also, misinformation and fake news are increased by the user without proper verification. Hence, it is necessary to restrict the spreading of fake information on mass media and to promote confidence all over the world. For this purpose, this paper recognizes the detection of fake news in an effective manner. The proposed methodology in detecting fake news consists of four different phases namely the data pre-processing phase, feature reduction phase, feature extraction phase as well as the classification phase. During data pre-processing, the input data are pre-processed by employing tokenization, stop-words deletion as well as stemming. In the second phase, the features are reduced by employing PPCA to enhance accuracy. Then the extracted feature is provided to the classification phase where LSTM-LF algorithm is utilized to classify the news as fake or real optimally. Furthermore, this paper utilizes four different datasets namely the Buzzfeed dataset, GossipCop dataset, ISOT dataset as well as Politifact dataset for evaluation. The performance evaluation and the comparative analysis are conducted and the analysis reveals that the proposed approach provides better performances when compared to other fake detection-based approaches.


  • Open Access

    Fake News Classification Using a Fuzzy Convolutional Recurrent Neural Network

    by Dheeraj Kumar Dixit, Amit Bhagat, Dharmendra Dangi

    In recent years, social media platforms have gained immense popularity. As a result, there has been a tremendous increase in content on social media platforms. This content can be related to an individual's sentiments, thoughts, stories, advertisements, and news, among many other content types. With the recent increase in online content, the importance of identifying fake and real news has increased. Although, there is a lot of work present to detect fake news, a study on Fuzzy CRNN was not explored into this direction. In this work, a system is designed to classify fake and real news using fuzzy logic. The initial feature extraction process is done using a convolutional recurrent neural network (CRNN). After the extraction of features, word indexing is done with high dimensionality. Then, based on the indexing measures, the ranking process identifies whether news is fake or real. The fuzzy CRNN model is trained to yield outstanding results with 99.99 ± 0.01% accuracy. This work utilizes three different datasets (LIAR, LIAR-PLUS, and ISOT) to find the most accurate model.


  • Sentiment analysis of social media data based on chaotic coyote optimization algorithm based time weight‐AdaBoost support vector machine approach

    by Dharmendra Dangi, Amit Bhagat, Dheeraj Kumar Dixit

    Summary: Sentiment analysis or opinion mining is exploited in business, customer services, and so forth, where people provide their opinions in the form of reviews. However, the people's opinions are in a perplexing form such as, sarcasm, irony, and implied meaning which can cause an impact on sentiment analysis. The only way to analyze these words is through context. Nevertheless, there still exist some issues, to tackle those issues, a lot of research has been conducted by focusing the feature engineering. However, the optimized output has not been acquired yet. Hence, we propose a novel method known as chaotic coyote optimization algorithm (COA) based time weight‐AdaBoost support vector machine (SVM) approach which can be used to attain the precise classifications in context. The proposed time weight‐AdaBoost SVM can be used to circumvent the drift concept issues and can be utilized for the perfect learning of data for further classifications. Further, the class imbalance issues can be overcome by adopting a modified CO algorithm, that is, the chaotic COA. Furthermore, the proposed work performance is analyzed with state‐of‐art works such as DICE, ABCDM, and SVM approaches. The comparative analysis shows that our proposed work classifies the social media content acquired from Twitter more accurately than the other works. Thus our work outperforms all the existing approaches in terms of accuracy, precision, recall, and F1 score.