Papers by MOHIT MAYANK (RA2111004010364)

2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
Fake News on social media platforms has attracted a lot of attention in recent times, primarily f... more Fake News on social media platforms has attracted a lot of attention in recent times, primarily for events related to politics (2016 US Presidential elections), healthcare (infodemic during COVID-19), to name a few. Various methods have been proposed for detecting Fake News. The approaches span from exploiting techniques related to network analysis, Natural Language Processing (NLP), and the usage of Graph Neural Networks (GNNs). In this work, we propose DEAP-FAKED, a knowleDgE grAPh FAKe nEws Detection framework for identifying Fake News. Our approach is a combination of the NLP-where we encode the news content, and the GNN technique-where we encode the Knowledge Graph (KG). A variety of these encodings provides a complementary advantage to our detector. We evaluate our framework using two publicly available datasets containing articles from domains such as politics, business, technology, and healthcare. As part of dataset pre-processing, we also remove the bias, such as the source of the articles, which could impact the performance of the models. DEAP-FAKED obtains an F1-score of 88% and 78% for the two datasets, which is an improvement of ∼21%, and ∼3% respectively, which shows the effectiveness of the approach.

Women Empowerment & Its Impact on Health Status in Bihar
Empowering women is an important subject to achieve targets for the sustainable development goals... more Empowering women is an important subject to achieve targets for the sustainable development goals of Bihar. There are several indicators to measure the empowerment of women. Health seeking information is one of the most important indicators in this regard. This study aims at identifying the levels and patterns of women empowerment in relation to health seeking behaviour in Bihar. A total of 45812 women were included in this study. NFHS -4 (National Family Health Survey) data was used for this study. The main emphasis of this study is towards the empowerment of women in terms of Health status and work. The major finding shows that 77.2 % of women were married and 20.2% were never in Union. 84.7% of women were currently working and 15.3% were not working. 86.7% women belong to rural and 13.3% belong to urban. In terms of Decision making of women there were some variables identified like Decision making in terms of spending money, Decision making in terms of health care, For household ...

India highly relies on the foreign crude oil supply, hence many listed firms in the National Stoc... more India highly relies on the foreign crude oil supply, hence many listed firms in the National Stock Exchange trade accord the crude oil prices. In this study, we materialize Brent Oil prices impact on three important Sectoral Indices, stock prices of NIFTY along with NIFTY 500 Index. Each sector accommodates those stocks, which endure a close relationship with the crude oil prices. We followed the model developed by (Lutz Killian, Cheolbeom Park, 2009) for selecting the sectoral indices and variable in oil market components. VAR and FEVD model assist us in understanding what determines Indian Oil market prices and whether oil prices affect the NIFTY sectoral index stock prices. We construct growth model to assess study further and followed guideline and tests, which are essential for VAR analyses. It is observed that only energy sectoral index respond to oil shock and global oil production impact Indian oil demand and oil prices whereas domestically oil price are determine by oil res...

5th International Conference on Data Mining and Applications (DMAP 2019), 2019
The slowness of legal proceedings in the common law legal system is a widely known fact. Any tool... more The slowness of legal proceedings in the common law legal system is a widely known fact. Any tool which could help reduce the time taken for the resolution of a case is invaluable. Common legal systems place a great importance on precedents and retrieving the correct set of precedents is considerably time consuming. Hence, for any case whose proceedings are in progress, if there are suitable prior cases, then the court has to follow the same interpretations that were passed in the prior cases. This is to ensure that similar situations receive similar treatment, thus maintaining uniformity amongst the legal proceedings across all courts at all times. Hence, precedent cases are treated as important as any other written law (a statute) in this legal system. In this paper, we propose two new approaches to solve this information retrieval problem wherein the system accepts the current case document as the query and returns the relevant precedent cases as the result. The first approach is to calculate the document similarity using Wordnet, which is a lexical database that could be leveraged to quantify the semantic relatedness between two documents, using a semantic network. The second approach is the use of a Siamese Manhattan Long Short Term Memory network, which is a supervised model trained to understand the underlying similarity between two documents.

arXiv (Cornell University), Dec 1, 2020
Recent word embeddings techniques represent words in a continuous vector space, moving away from ... more Recent word embeddings techniques represent words in a continuous vector space, moving away from the atomic and sparse representations of the past. Each such technique can further create multiple varieties of embeddings based on different settings of hyper-parameters like embedding dimension size, context window size and training method. One additional variety appears when we especially consider the Dual embedding space techniques which generate not one but two-word embeddings as output. This gives rise to an interesting question-"is there one or a combination of the two word embeddings variety, which works better for a specific task?". This paper tries to answer this question by considering all of these variations. Herein, we compare two classical embedding methods belonging to two different methodologies-Word2Vec from window-based and Glove from count-based. For an extensive evaluation after considering all variations, a total of 84 different models were compared against semantic, association and analogy evaluations tasks which are made up of 9 open-source linguistics datasets. The final Word2vec reports showcase the preference of non-default model for 2 out of 3 tasks. In case of Glove, non-default models outperform in all 3 evaluation tasks.
Uploads
Papers by MOHIT MAYANK (RA2111004010364)