Abstract

Cultural objects are highly interpretive and complex in nature. Though technological advancements have made it possible to digitize and preserve knowledge of cultural value, capturing details of such objects in-situ has rarely been explored. In this thesis, we develop a platform called Curarium for indepth exploration of cultural collections, within and outside a museum setting. A focus group of 17 researchers gathered cultural collections on a trip to Odisha. The collections contain information pertaining to Pattachitra paintings, Gotipua performances, sustainable crafts, museum objects and processions. The data-sets are unique in nature and content, as they provide for an interplay between different kinds of objects. In this thesis, we examine the cultural value in objects unexplored before - like processions, and what they comprise. To accommodate the different kinds of data, we develop a meta-data structure that would encapsulate all the relevant information. We import the curated data collection into Curarium and utilize the various in-house tools to discover patterns, create annotations, collaborate and visualize the data. Curarium provides a novel approach in delving deep into a cultural object. However, we recognize a gap in cross-referencing objects within its natural environment. In lieu of this, the thesis proposes developing narratives about cultural objects as an approach to capturing information. We develop a platform to generate narratives based on the digital surrogates. We conduct a user study with the focus group to develop narratives on the aforementioned data-sets on a platform called Narratavium. On further research, we recognize these narratives to be of three types - within-object, within-collection, and user generated thematic narratives. Upon recognizing plots within art objects and identifying themes, we account for the human experience in interacting with these cultural objects in their natural environment. This narrows the removed appreciation of the culture by the audience. In this thesis, we utilize sequential art methods to study Pattachitra paintings, Aristotlean narrative theories to study processions and performances, and qualitative analysis to generate themes. By visualizing the narrative information, we gain insights into nuances of the objects and the collections as a whole. We use charts and clusters to extract popular themes in a collection. We develop methods to identify conflict points in a narrative and understand transitions in a story plot. We also study information retention in the process of re-narration, and relevant objects in a collection through frequently told narratives.

Abstract

Dopamine plays a major role in learning and reward. Dopaminergic neurons in the ventral tegmental area (VTA) exhibit the discrepancy between expected and actual rewards known as reward prediction error (RPE). But how these signals are computed in the brain remains unknown. One of the earliest attempts of investigation of animal learning involved pairing an unconditioned stimulus (US) with a cue or conditioned stimulus (CS) and observing that animal starts responding to the CS after some point in time. This is the basis of Pavlovian learning or classical conditioning, a fundamental learning mechanism in animals. The model described here focuses on the mechanism of reward prediction error within Pavlovian learning and does not deal with other conditioning phenomena. To acquire a deeper understanding of the roles of the cerebral structures involved in RPE computation, we need a neuro-computational model implicating them more faithfully in Pavlovian learning. The approach described here is a model that proposes a circuit involving a dissociation between magnitude expectation and timing expectation and explaining more precisely how the computation of the reward prediction error happens inside the VTA. The model described here proposes that the two dimensions involved in computation of reward prediction errors i.e., magnitude and time could be computed separately and later combined unlike the way it is done in traditional reinforcement learning models. The model is built on biological evidences and is able to reproduce various aspects of classical conditioning, namely, the progressive cancellation of the predicted reward, the predictive firing from conditioned stimuli, the twin peaks of dopamine firing and delineation of early rewards by showing more firing for sooner early rewards and less for early rewards that occur with a longer latency in accordance with biological data. Key predictions for experiments are made regarding how neural substrates execute this computation which would validate the model. Potential implications for the reinforcement learning theory are also discussed.

Abstract

The structure of built environment is defined by the collection of fundamental units contained in it. Two of the most basic units in an urban setting are Roads and Buildings. The buildings form most of the origin and destination pairs for intra-city movements and the road-networks aid these movements. The basic aim of this thesis is to identify patterns of arrangements of these elementary units in any urban agglomeration along with deriving a syntactic meaning out of the arrangement geometry and secondly, how the movements patterns and dynamic occupancy of spaces are often affected by the synergy of roads and buildings. We try to identify combinations of arrangement of these two that increase the odds in favor of increasing attractor values of spaces. In past, several studies were carried out to extract patterns in urban environment which were often driven by considering networks only. A few studies paid attention to buildings and their characteristics such as their volumetric capacities and their locations along the network. The approach we have chosen to define symmetries and regularities in structures is hybrid in nature as it considers both buildings and road-networks as well as their intrinsic interactions such that the buildings and roads in closer vicinity inherit the properties of each other. The spatial indices we used for analyzing built environments are based on navigational properties of any location which suggest accessibility of the location depending on its connectivity with neighborhoods. These indices are motivated by a combination of Space Syntax configurational theory that uses topological (Angular & Segment) distances along network and Urban Network Analysis which has metric distances as basis for accessibility computations. The accessibility based on topological as well as metric computations is defined as function of how often a spatial unit lies on the shortest paths while commuting all origin-destination pairs in its neighborhood, how many of surrounding places can be reached from this place, how compactly packed is the neighborhood for a given set of fixed radii, and do the shortest paths between origin-destination pairs resemble straightest distances. These characteristics can be discussed for both buildings and roads. We use spatial autocorrelation for our chosen accessibility indices to analyze significance of occurrence of specific patterns of neighborhoods for city of Hyderabad, India, and thus consider not only spatial units but areas as whole. We discuss the inconsistencies in methodologies used, and propose a weight metrics for urban road network, weights are driven by dimensions of buildings. This enables us to reduce computational complexity by a significant margin using road networks as the only analysis layer for making configurational computations. We verify that it is intrinsic property of spatial organization that more similar areas tend to occur in closer vicinity of each other by using K Means clustering. In the process, we also propose that the clusters formed with varying radii of analysis are suggestive of spatial properties of urban environment. Lastly, we present a data driven methodology to classify regions in terms of amount vehicular traffic. In this technique, Average Annual Daily Counts (AADT) of vehicular traffic are used to represent roads into three categories of high, medium and low which are then superimposed on buildings. The chosen spatial indices form feature vectors for training the model while the vehicular traffic categories superimposed on buildings act as prediction target labels. To get the best accuracy model, we compare performances of Logistic Regression Classification model, Decision Tree Classification model and ensemble based Gradient Boosted Classification model. The ensemble based model using gradient boosting algorithm outperforms all other models in this classification task. While discussing all methodologies to denominate areas in terms of their symmetry and constrained by relative carriage of vehicular traffic, we go from a local measure of trip distances towards global trip distances that implies we go from inspection of nearby regions in close proximity of area under observation towards larger distances. This process enables us to draw comparisons between areas corresponding to their obvious choices of being preferred for various trip distances. For example, an area being preferred for short trip distances might not be a good fit for longer trips and vice versa. The approaches presented in this can draw conclusive reports from the perspective of architectural and infrastructural planning for new city sites and modifying the existing ones.

Abstract

The amount of videos recorded and shared on the internet has grown massively in the past decade. The most of it is due to the cheap availability of mobile camera phones and easy access to social media websites and their mobile applications. Applications such as Instagram, Vine, Snapchat allows users to record and share their content in matter of seconds. These three are not the only such media sharing platform available but the number of active monthly users are 600 , 200, and 150 million respectively indicate the interest people have in recording, sharing and viewing their content [1,3]. The number of photos and videos collectively shared on instagram alone crosses 40 billion [1]. Vine contain approximately 40 million videos created by the users [3] and on a daily basis played 1 billions times. This cheaply available mode of data can empower many learning tasks which require huge amount of curated data. Also the videos contain novel viewpoints, and reflect real world dynamics. Different from the content available on older established websites such as Youtube, the content shared here is smaller in length (typically few seconds), contains description and associated hash-tags. Hash-tags can be thought of as keywords assigned by the user to highlight the contextual aspect of the shared media. However, unlike english words these don’t have a definite meaning associated to them as the description is heavily reliant on the content, along which the hash-tags are used. To clearly decipher the meaning of the hash-tag one requires the associated media. Hence, Hash-tags are more ambiguous and difficult to categorise than English words. In this thesis, we attempt to shed some light on applicability and utility of videos shared on a popular social media website vine.co. The videos shared here are called vines and are typically 6 seconds long. They contain with them description composed of a mixture of english words and hash-tags. We try recognising actions and recommend hash-tags to an unseen vine by utilising the visual and the semantic content and the hash-tags provided by the vines respectively. By this we try to show how this untapped resource of popular social media format can prove beneficial for resource intensive tasks which require huge amount of curated data. Action recognition deals with categorising the action being performed in a video to one of the seen categories. With the recent developments, considerable precision is achieved on established datasets. However, in an open world scenario, these approaches fail as the conditions are unpredictable. We show how vines are a much difficult categories of videos with respect to the videos currently in circulation for such tasks. To avoid manual annotations for vines we develop a semi-supervised bootstrapping approach. If one is to manually annotate vines this would defeat the purpose of easily available vines. We iteratively build an efficient classifier which leverages the existing dataset for 7 action categories and also the visual, semantic information present in the vines. The existing dataset forms the source domain and the vines compose the target domain. We utilise semantic word2vec space as a common subspace to embed video features from both, labeled source domain and unlabeled target domain. Our method incrementally augments the labeled source with target samples and iteratively modifies the embedding function to bring the source and target distributions together. Additionally, we utilise a multi-modal representation that incorporates noisy semantic information available in form of hash-tags. Hash-tags form an integral part of vines. Adding more and relevant hash-tags can expand the categories for which a vine can be selected. This enhances the utility of vines by providing missing tags and expanding the scope for the vines. We design a Hash-tag recommendation system to assign tags for an unseen vine from 29 categories. This system uses a vines’ visual content only after accumulating knowledge gathered in an unsupervised fashion. We build a Tag2Vec space from millions of hash-tags using skip-grams using a corpus of 10 million hash-tags. We then train an embedding function to map video features to the low-dimensional Tag2vec space. We learn this embedding for 29 categories of short video clips with hash-tags. A query video without any tag-information can then be directly mapped to the vector space of tags using the learned embedding and relevant tags can be found by performing a simple nearest-neighbor retrieval in the Tag2Vec space. We validate the relevance of the tags suggested by our system qualitatively and quantitatively with a user study.

Abstract

Quantum information theory has emerged as one of the new frontiers of science and technology over the last few decades. Unlike classical information theory that deals with the classical bit, quantum information theory is centred around the concept of a qubit. In contrast to the classical bit that can either be a 0 or 1, the qubit exists in a superposition of both states at the same time. The importance of quantum resources is evident from the fact that are certain information processing tasks like teleportation which cannot be accomplished with only classical resources and even though there are certain tasks like secret sharing which have classical counterparts, their outputs are greatly enhance when the classical resources are combined with quantum resources. While quantum superposition and entanglement are wellestablished quantum resources, recently, significant research has been carried out to explore the possibility of quantum coherence as a resource for information processing applications. This thesis is divided into four chapters. While the first two chapters deal with the fundamentals of quantum information theory and quantum coherence, the last two chapters primarily deal with the two research problems on quantum coherence. The first chapter serves as a revision of the important introductory concepts of quantum information theory, starting with the significance of the famous Stern-Gerlach experiment and the rise of randomness to mathematical formalism and postulates of quantum mechanics. Then, we explore the connection between randomness and lack of information and further explore how classical information is different from quantum information alongwith a brief overview of its corresponding measures. Finally, the chapter ends with a layout of widelyused quantum resources along with its utility in some of the famous information processing tasks. The second chapter mainly deals with a brief synopsis on quantum coherence. At first, it discusses the formulation of resource theory of quantum coherence, which is followed by an introduction to the widely accepted framework of quantifying coherence and some of the popularly used coherence quantifiers. Finally, the chapter concludes with the application of coherence in the fields of quantum thermodynamics, quantum algorithms, interference phenomena and phase discrimination. The third chapter addresses the first research topic of the thesis : broadcasting of quantum coherence. As quantum coherence has recently emerged as a key candidate for use as a resource in various quantum information processing tasks, hence, it is of utmost importance to explore the possibility of creating a greater number of coherent states from an existing coherent pair. This process is known as broadcasting of coherence. This chapter starts with a brief discussion on the famous no-cloning theorem, followed by an overview of approximate cloning transformations. After that, the motivation behind broadcasting of coherence is explored along with an introduction to the definitions of optimal and non-optimal broadcasting. In both these definitions, the most general two-qubit state is taken as the input to the cloner, while the most incoherent states are used as blank states of the cloner. This chapter leads to two important results. Firstly, it has been proved that while optimal broadcasting is not possible (for both local and non-local cloners), nonoptimal broadcasting cannot be ruled out. Secondly, in case of non-optimal broadcasting, the coherence introduced in the output states of the cloner will always be lesser than the initial coherence of the input state. Finally, three classes of mixed states, namely, the statistical mixture of the most coherent state (MCS) and the most incoherent state (MIS), the Wernerlike states (WLS) and the Bell-diagonal states (BDS), are taken up for obtaining their respective ranges of non-optimal broadcasting in terms of their corresponding input state parameters. The fourth and final chapter deals with the second research topic of the thesis : some peculiar properties of robustness of coherence (ROC). Here, it has been shown that robustness of coherence, in contrast to many popular quantitative measures of quantum coherence derived from the resource theoretic framework of coherence, may be sub-additive for a specific class of multi-partite quantum states. Furthermore, this chapter also highlights how the subadditivity is affected by admixture with other classes of states for which ROC is superadditive. Moreover, it has been shown that pairs of quantum states may have different orderings with respect to relative entropy of coherence, l1-norm of coherence and ROC and the difference in ordering for coherence measures chosen pairwise has been numerically studied.

Abstract

In the thesis, an ontology and event grammar of tennis is proposed in order to enhance the methods of analysis in tennis. This work specifically focuses on the analysis required for improving the game from the coach’s point of view. Our ontological study has a vocabulary involving about 760 reusable terms related to tennis which are broadly divided into 12 top classes. The scope of this thesis deals primarily with three classes ‘play’, ‘score’ and ‘court’ and related terms out of the twelve. These terms and their relationships are defined with the help of event trees, score graphs and labelled images which are based on the rules legislated by International Tennis Federation. Any game of tennis involves a particular sequence of events. With the help of event trees, a generative event grammar of any play has been designed. This grammar generates all possible legal sequences of events that can take place in a game of tennis. However, a particular game is a unique sequence of such possible events. A game of tennis is represented as a finite state automaton, at any given point it can be in exactly one defined state. Annotated data is crucial in any form of analysis. We have created a real time annotator for tennis on the android platform based on the proposed event grammar. This integration of grammar into the application reduces the error rate and also makes the process efficient. The annotated file is then processed for generating play statistics at two levels. First, basic features such as success rates of shots/serves, number of forehands/backhands hit/miss etc. are analyzed. These features are very similar to those presented during the broadcast tennis videos in major tournaments although our annotation has more data like sub-events. Secondly, we infer sub-events between shots. Such detailed annotation points towards deeper inquiry as to why a shot was not executed properly, if it failed. An ergonomic and easy to replicate video documentation eight camera standard for the game of tennis is proposed. For deeper analysis, we create a data set of (singles) tennis games in accordance with the reduced version of the standard. Computationally two main features were extracted from this video data set: A. Player detection by a generalized feature based motion tracking algorithm, and B. Ball tracking by an improvised object-and-trajectory based algorithm. Every shot played is defined as a 18-feature tuple in the ontology. Selected features from the definition were computed by extracting ball trajectory and player position in real world situations. The features thus extracted are then classified and validated using SVM and KNN techniques. The features extracted along with their accuracies are: spin of the ball (83.85%), trajectory height (95.56%), position (94.65%) and number of bounces (98.93%). Additional application of shot prediction (88.75%), which predicts the next likely shot to be hit based on the player and ball bounce positions, was also implemented. An adaptive probabilistic model was developed to analyze a player’s game by predicting the conditional probabilities of an event based on a previously occurred event. A graph based on event trees is constructed to store the occurrences of a particular event and features. The data changes dynamically as the game proceeds and at any given point will give an experimental probability of the next likely events based on the current and past events. Proposed analysis reduces search space for coach to identify areas of improper execution and work towards improving player’s performance.

Abstract

Satellite imagery in the recent past has gone through numerous advancement. Different satellite sensors have been developed with the capability to capture the data at different scales from coarse to very fine. The finer resolution data provides detailed information which helps in improving the object detection for more number of land cover classes. Satellite imagery forms the backbone of remote sensing. Remote sensing has a wide range of applications in Earth sciences like geology, military, economic and humanitarian purposes. Urban remote sensing is useful for analysing and planning. Building detection is one of the most important aspects of urban remote sensing. Building footprint detection is very useful in wide range of applications like disaster management, urban planning, cartography, environment modeling, all require knowledge of man made structures. Even now, mapping of buildings is done using remote sensing based on visual interpretation or manual digitizing of digital images. These methods are tedious, time consuming, requires qualified people, therefore it has virtually no scope for real-time applications. This work presents an approach to automatic building detection from very high resolution (VHR) satellite images. The work includes discussion of various image processing techniques used and challenges faced with detection of different building models. Monocular satellite data is used for this work. Satellite images typically contain elements like development areas, vegetation, water bodies, barren land etc. Development areas include buildings, roads, pavements and other such man-made entities. The first task of building detection process is to remove the natural entities and focus on development regions. This task is realized using Independent Component Analysis (ICA). Three input planes derived from the LAB and LUV colorspace are used as input to the ICA which in turn converts them into three independent output planes. One of these output planes primarily contains man-made structure pixels and other two primarily contain vegetation and other natural entities. Development areas are detected using pixels obtained from the plane and appropriate thresholding. The only drawback of this technique is buildings are obtained in the form of individual pixels and as a result, object-level performance of the detection is not as good as its pixel-level performance. The second phase of this work builds on the learning of ICA based building detection. The candidate building pixels obtained through ICA are now used to extract maximally stable extremal regions (MSER) which are then filtered using geometric properties to obtain final candidate buildings. The technique is aimed at improving object-level performance. The achieved Precision of 80.64% and Recall of 83.65 % in case of object-level evaluation. The work offers an unsupervised building detection technique which is robust towards size, shape, color, types of rooftops and shadows. A wide test image set consisting of 15 localities is used to evaluate the performance of the complete detection process. This technique achieved higher object-level performance compared to the only ICA-based technique. The ICA and MSER combined approach have potential to detect buildings under different scenarios, not compromising with accuracy.

Abstract

Statistical Machine Translation (SMT) is an automated approach to Natural-Language translation, that utilizes statistical models generated from the bilingual parallel corpora. The system is thus funda- mentally reliant on the bilingual parallel corpora, to translate text from one language to another. Ad- ditionally, in the past several decades, research in SMT has been focused on augmenting syntactic and linguistic information to the statistical models to generate better translations. Thus, construction of the aforementioned linguistic resources like bilingual parallel corpora and corpora enriched with syntactic and linguistic information plays a key role in building better SMT systems. SMT work for the English-Hindi languages are limited and have been resource deprived, especially for the Hindi language. The prime motivation for the research in this thesis is to bridge the gaps in the level of resources available for Hindi language and the English-Hindi language pair, from an SMT per- spective. The initial experiments at building a Hindi-English SMT system with Part-Of-Speech (POS) augmented models yielded unfavourable results, with translations that are no better than the plain statis- tical models. Root cause analysis revealed fundamental flaws like lack of better bilingual corpora and better syntactic models, which hinders the improvements to SMT system, thus setting the goal of this thesis towards addressing these issues. Firstly, we start by presenting several parallel corpora for English$Hindi and talk about their na- tures and domains. We also discuss briefly a few previous attempts in MT for translation from English to Hindi. The lack of uniformly annotated data makes it difficult to compare these attempts and pre- cisely analyse their strengths and shortcomings. With this in mind, a standard pipeline to provide uni- form linguistic annotations to these resources using the state-of-art NLP technologies is presented. The benchmark scores for various English!Hindi SMT systems are constructed using the aforementioned parallel corpora. A total of 1,37,578 sentences were cleaned and MT systems were benchmarked as part of this work. Subsequently which, this thesis talks about several digital text sources from different domains in English and Hindi languages which were processed with the intention of extracting parallel sentences. We faced several difficulties while extracting text content from different documents, especially the non- linear presentation of text in varying page layouts. We focus on this problem of linearizing the text from these digital sources by proposing a clustering based algorithm to eliminate the noise. The effort undertaken helped us process the raw sources available in different formats, different fonts and varying page layouts to produce 79,422 English and 68,584 Hindi sentences with comparable meanings across both languages. Lastly, a semi-automated framework is presented to enable speeding up dependency annotation task for corpora. We talk about the slow game of pass-the-parcel in between both the automation and hu- man sides which finally results in raw corpora being transformed into dependency annotated sentences. The methods of automation chosen to overcome the laborious and time-consuming process of corpora annotation are discussed. Along side which the errors and multiple analyses that result through the task of annotation and ways to recover are also discussed in detail. A total of 20,968 dependency annotated Hindi sentences and 7,120 Urdu sentences are created using the mentioned framework. Overall, the thesis tries to present three different efforts undertaken to quench the thirst for resources in the field of English$Hindi SMT.

Abstract

Complex noun sequences in Hindi can be formed by the sequences of nouns and genitives. In Hindi, the genitive marker is “k¯a”, and its allomorphic variations are “ke” and “k¯i”. When two or more nouns occur without any intervening post-positions, it is known as compound noun. Following are some examples of complex noun sequences: (1) “jil¯a cun¯ava adhik¯ar¯i” (district election officer), (2) “tila k¯i mit.h¯a¯i k¯i duk¯ana” (shop of sweets made with sesame) and (3) “upabhokt¯a ad¯alata ke vak¯ila” (consumer court’s lawyer). The rightmost noun is the head of the whole construction. The inner structure of the sequence can be quite complex. In it, (a) nouns within the sequence can modify the rightmost head or (b) the local head can modify another local head or the head of the complex noun sequence. For example, in (1), “adhik¯ar¯i” is the head and both “jil¯a” and “cun¯ava” are modifying “adhik¯ar¯i” thus having a structure (jil¯a (cun¯ava adhik¯ar¯i)). But, the complex sequence in (2) has a structure where “tila” modifies “mit.h¯a¯i” and “mit.h¯a¯i” in turn modifies “duk¯ana”. So the structure is ((tila k¯i mit.h¯a¯i) k¯i duk¯ana). More number of nouns within a sequence, more complex is the structure. From the Hindi Treebank data, we have obtained 85.37%, 12.54% and 1.80% of the sequences having three, four and five nouns respectively. In this thesis, we attempt to bracket the local sub-structure of a complex noun sequence which is termed as constituency parsing. Constituency parsing recursively builds the inner structure of the complex noun sequence. It is a very significant NLP task because the interpretation of sequence depends on the correct identification of its inner structure. We explore both syntactic and statistical method for predicting the bracketing of the complex noun sequences. In Hindi, the genitive marker agrees with the head of the sub-sequence modified by it. This clue has been used in our syntactic approach. In statistical approach, we have mainly exploited the affinity factor of a head and its modifier based on the frequency of occurring together in the corpus. The method has been augmented by introducing the semantic class information for the head and modifier nouns from Hindi WordNet. Finally, we combine the two methods and implement a hybrid approach for bracketing complex noun sequences. Using this, we have obtained 85.85% accuracy. In this thesis, we show that the identification of the inner structure of complex noun sequence helps in determining the translation. For this experiment, we take three-word noun compounds of English and translate them into Hindi. The strategy of the translation is determined by our observation of English-Hindi parallel corpora where we observe (and others have reported also) that English licenses multiword noun compound more frequently than what Hindi does. Hindi prefers syntactic phrases where a genitive post-position is inserted between the head and the modifier. In the case of compounds with three nouns, we propose that inner bracketing helps in determining the insertion of the genitive marker. For the left bracketing structure ((e1 e2) e3), we predict that the genitive will be inserted before e3. For the right bracketing structure (e1 (e2 e3)), the genitive will be inserted after e1. This hypothesis is tested, and we get the accuracy of 68.86%, 71.99% and 59.12% for BNC, ukWaC and ILCI corpus respectively.

Abstract

Of late, sentiment analysis has transpired to be a critical cog in a slew of diverse Natural Language Processing tasks like recommendation systems, question answering, and business intelligence products to name a few. At its core, sentiment analysis is the process of analyzing emotions in a given piece of text, where the excerpt at hand is predominantly classified as carrying either a positive or a negative polarity. While the study of sentiment analysis in English has been proliferating, to say the least, the task has hardly been probed in Telugu. In this thesis, we attempt to get down to the brass tacks of sentiment analysis for the language popularly known as the Italian of East. While sentiment analysis in itself poses tremendous challenges, an additional problem in Telugu, that has restrained people from conducting active research, is the availability of appropriate data. We thus address the latter first, to ensure that the former problem is tackled more effectively. To address data availability, using a set of well-defined annotation guidelines, we first manually annotate Telugu texts with either positive, negative or neutral tag. The annotated data is then used to carry the sentiment analysis task, where a variety of machine learning algorithms are employed to handle both binary (only positive and negative tags) and ternary (positive, neutral and negative tags) sentiment analysis classification problems. Our experiments reveal that while a tad complex classifier like Random Forests can rule the roost in the case of binary classification task, a simple classifier like logistic regression can come up trumps should the task be framed as a ternary classification problem. It is a known fact that learning algorithms improve with an increase in the amount of training data. However, manually annotating data is practically difficult and expensive. To address these issues, we employ a novel approach of Hybrid Query Selection Strategy to increase the annotated data, where a set of classifiers are adopted to annotate data. Experiments show that our approach effectively achieves this with a minimal error rate. We also use active learning to classify sentences according to their polarities, thereby achieving our end goal.