• AMLAN CHAKRABARTI

      Articles written in Sadhana

    • Demonetization and its aftermath: an analysis based on twitter sentiments

      PARAMITA RAY AMLAN CHAKRABARTI BHASWATI GANGULI PRANAB KUMAR DAS

      More Details Abstract Fulltext PDF

      Sentiment analysis has become a very useful tool in recent times for studying people’s opinions, sentiments and subjective evaluation of any event of social and economic relevance, and in particular, policy decisions. The present paper proposes a framework for sentiment analysis using twitter data for the ’demonetization’ effort of the Government of India. The paper employs twitter data using Twitter API. The methodology of the paper involves collection of data from twitter from different cities of India using geolocation and preprocessing followed by a lexicon-based approach to analyse users’ sentiments over a period of five weeks preceding the policy announcement. In addition to this, the paper also attempts to analyse the sentiments of specific groups of people representing diverse interest groups.

    • An information-theoretic graph-based approach for feature selection

      AMIT KUMAR DAS SAHIL KUMAR SAMYAK JAIN SAPTARSI GOSWAMI AMLAN CHAKRABARTI BASABI CHAKRABORTY

      More Details Abstract Fulltext PDF

      Feature selection is a critical research problem in data science. The need for feature selection has become more critical with the advent of high-dimensional data sets especially related to text, image and microarray data. In this paper, a graph-theoretic approach with step-by-step visualization is proposed in the context of supervised feature selection. Mutual information criterion is used to evaluate the relevance of the features with respect to the class. A graph-based representation of the input data set, named as feature information map (FIM) is created, highlighting the vertices representing the less informative features. Amongst the more informative features, the inter-feature similarity is measured to draw edges between features having high similarity. At the end, minimal vertex cover is applied on the connected vertices to identify a subset of features potentially havingless similarity among each other. Results of the experiments conducted with standard data sets show that the proposed method gives better results than the competing algorithms for most of the data sets. The proposed algorithm also has a novel contribution of rendering a visualization of features in terms of relevance andredundancy.

    • Accelerated Single-Linkage algorithm using triangle inequality

      PAYEL BANERJEE AMLAN CHAKRABARTI TAPAS KUMAR BALLABH

      More Details Abstract Fulltext PDF

      Single-Linkage algorithm is a distance-based Hierarchical clustering method that can find arbitrary shaped clusters but is most unsuitable for large datasets because of its high time complexity. The paper proposes an efficient accelerated technique for the algorithm with a merging threshold. It is a two-stage algorithm with the first one as an incremental pre-clustering step that uses the triangle inequality method to eliminate the unnecessary distance computations. The incremental approach makes it suitable for partial clustering of streaming dataalong with the collection. The second step using the property of the Single-Linkage algorithm itself takes a clustering decision without comparing all the patterns. This method shows how the neighbourhood between the input patterns can be used as a tool to accelerate the algorithm without hampering the cluster quality. Experiments are conducted with various standard and large real datasets and the result confirms its effectiveness for large datasets.

    • A strong intuitionistic fuzzy feature association map-based feature selection technique for high-dimensional data

      AMIT KUMAR DAS SAPTARSI GOSWAMI AMLAN CHAKRABARTI BASABI CHAKRABORTI

      More Details Abstract Fulltext PDF

      In this work, a graph-based approach has been adopted for feature selection in case of highdimensional data. Feature selection intends to identify an optimal feature subset to solve the given learning problem. In an optimal feature subset, only relevant features are selected as ‘‘members’’ and features that haveredundancy are considered as ‘‘non-members’’. This concept of ‘‘membership’’ and ‘‘non-membership’’ of a feature to an optimal feature subset has been represented by a strong intuitionistic fuzzy graph. The algorithm proposed in this work at first maps the feature set of the data as the vertex set of a strong intuitionistic fuzzy graph. Then the association between features represented as an edge-set is decided by the degree of hesitation between the features. Based on the feature association, the Strong Intuitionistic Fuzzy Feature Association Map (SIFFAM) is developed for the datasets. Then a sub-graph of SIFFAM is derived to identify features with maximal non-redundancy and relevance. Finally, the SIFFAM based feature selection algorithm is applied on very high dimensional datasets having features of the order of thousand. Empirically, the proposed approach SIFFAM based feature selection algorithm is found to be competitive with several benchmark feature selection algorithms in the context of high-dimensional data

  • Sadhana | News

    • Editorial Note on Continuous Article Publication

      Posted on July 25, 2019

      Click here for Editorial Note on CAP Mode

© 2021-2022 Indian Academy of Sciences, Bengaluru.