Rajendra Prasath

Shared Task on Sentiment Analysis in Indian Languages SAIL Tweets - An Overview

Sentiment Analysis in Twitter has been considered as a vital task for a decade from various academic and commercial perspectives. Several works have been performed on Twitter sentiment analysis or opinion mining for English in contrast to the Indian languages. Here, we summarize the objectives and evaluation of the sentiment analysis task in tweets for three Indian languages namely Bengali, Hindi and Tamil. This is the first attempt to sentiment analysis task in the context of Indian language tweets. The main objective of this task was to classify the tweets into positive, negative, and neutral polarity. For training and testing purpose, the tweets from each language were provided. Each of the participating teams was asked to submit two systems, constrained and unconstrained systems for each of the languages. We ranked the systems based on the accuracy of the systems. Total of six teams submitted the results and the maximum accuracy achieved for Bengali, Hindi, and Tamil are 43.2i¾?%, 55.67i¾?%, and 39.28i¾?% respectively.

Learning Age and Gender of Blogger from Stylistic Variation

We report results of stylistic differences in blogging for gender and age group variation. The results are based on two mutually independent features. The first feature is the use of slang words which is a new concept proposed by us for Stylistic study of bloggers. For the second feature, we have analyzed the variation in average length of sentences across various age groups and gender. These features are augmented with previous study results reported in literature for stylistic analysis. The combined feature list enhances the accuracy by a remarkable extent in predicting age and gender. These machine learning experiments were done on two separate demographically tagged blog corpus. Gender determination is more accurate than age group detection over the data spread across all ages but the accuracy of age prediction increases if we sample data with remarkable age difference.

Mining Intelligence and Knowledge Exploration

Feature selection refers to a problem to select a subset of features which are most optimal for intended tasks. As one of well-known feature selection methods, clustering features into several groups and picking one feature from each group have been used for unsupervised feature selection. Since the purpose of clustering in feature selection is to select a feature from each group, the quality of the feature to be selected should be considered in the clustering process. In this paper, we propose a feature selection method using hierarchical clustering. A new similarity measure between two feature groups is defined by directly using the representative feature in each group. Experimental results show that our method can select good features even for supervised learning.

Multimodal Sentiment Analysis Using Deep Neural Networks

Due to increase of online product reviews posted daily through various modalities such as video, audio and text, sentimental analysis has gained huge attention. Recent developments in web technologies have also enabled the increase of web content in Hindi. In this paper, an approach to detect the sentiment of an online Hindi product reviews based on its multi-modality natures (audio and text) is presented. For each audio input, Mel Frequency Cepstral Coefficients (MFCC) features are extracted. These features are used to develop a sentiment models using Gaussian Mixture Models (GMM) and Deep Neural Network (DNN) classifiers. From results, it is observed that DNN classifier gives better results compare to GMM. Further textual features are extracted from the transcript of the audio input by using Doc2vec vectors. Support Vector Machine (SVM) classifier is used to develop a sentiment model using these textual features. From experimental results it is observed that combining both the audio and text features results in improvement in the performance for detecting the sentiment of an online product reviews.

Malware Detection in Big Data Using Fast Pattern Matching: A Hadoop Based Comparison on GPU

In big data environment, hadoop stores the data in distributed file systems called hadoop distributed file system and process the data using parallel approach. When the cloud users store unstructured data in cloud storage, it becomes very important for cloud providers to secure those data. To provide malware security, cloud service providers should scan the whole contents of the database, which is a very time intensive job. It may even take days to complete the tasks. The main aim of the proposed work is to reduce the processing time by introducing Graphics Processing Unit (GPU) in hadoop cluster. The proposed work integrates two text pattern matching algorithms with the map-reduce programming model for faster detection of malware in big data. The results of our study indicate that use of GPU decreases the processing time of text pattern matching algorithms in big data hadoop.

Finding potential seeds through rank aggregation of web searches

This paper presents a potential seed selection algorithm for web crawlers using a gain - share scoring approach. Initially we consider a set of arbitrarily chosen tourism queries. Each query is given to the selected N commercial Search Engines (SEs); top msearch results for each SE are obtained, and each of these mresults is manually evaluated and assigned a relevance score. For each of m results, a gain - share score is computed using their hyperlinks structure across N ranked lists. Gain score of each link present in each of m results and a portion of the gain score is propagated to the share score of each of m results. This updated share scores of each of m results determine the potential set of seed URLs for web crawling. Experimental results on tourism related web data illustrate the effectiveness of the proposed seed selection algorithm.

Learning age and gender using co-occurrence of non-dictionary words from stylistic variations

This work attempts to report the stylistic differences in blogging for gender and age group variations using slang word co-occurrences. We have mainly focused on co-occurrence of non dictionary words across bloggers of different gender and age groups. For this analysis, we have focused on the feature use of slang words to study the stylistic variations of bloggers across various age groups and gender. We have modeled the co-occurrences of slang words used by bloggers as graph based model where nodes are slang words and edges represent the number of cooccurrences and studied the variations in predicting age groups and gender. We have used demographically tagged blog corpus from ICWSM Spinner dataset for these experiments and used Naive Bayes classifier with 10 fold cross validations. Preliminary results shows that the concurrence of of slang words could be a better choice for predicting age and gender.

MiW : An MCC-WMSNs Integration Approach for Performing Multimedia Applications

The popularity of multimedia applications are growing day-by-day. Emerging Mobile Cloud Computing (MCC) and Wireless Multimedia Sensor Networks (MCC-WMSNs) help to work efficiently with these multimedia applications. The advantage of integrating MCC with WMSNs is that the data gathered by sensor nodes can be accessible from anywhere and at anytime by the users. In this context, there exists several issues such as battery life of the multimedia sensors, processing power, and storage etc. To solve these problems, in this work a MCC-WMSNs integration technique is proposed by using a cloudlets based integration algorithm named as CLIW which mainly works with CLIW-1 and CLIW-2 schemes where both the schemes focus on minimizing energy consumption. The simulation results indicate that CLIW-1 and CLIW-2 schemes are able to prolong the network lifetime of integrated WMSNs.

Algorithms for distributed sorting and prefix computation in static ad hoc mobile networks

Distributed processes with message passing strategy, communicate among themselves by exchanging pieces of information to perform exclusive access to achieve the tasks in a distributed fashion. In this paper, we consider sorting and prefix computation problems with n elements distributed over a number of communication processors in a distributed system. The proposed distributed sorting algorithm improves the performance of each processor without creating copies of elements at intermediate processors. Also all processors do not necessarily perform the disjoint comparison exchange operations and the proposed algorithm works with the identity of processors. The proposed algorithms are based on token based message passing strategy for distributed sorting and prefix computation problems on static ad hoc mobile networks. These algorithms could possibly be extended to dynamic ad hoc mobile networks.

Distributed representations to detect higher order term correlations in textual content

Case Based Reasoning(CBR), an artificial intelligence technique, solves new problem by reusing solutions of previously solved similar cases. In conventional CBR, cases are represented in terms of structured attribute-value pairs. Acquisition of cases, either from domain experts or through manually crafting attribute-value pairs from incident reports, constitutes the main reason why CBR systems have not been more common in industries. Manual case generation is a laborious, costlier and time consuming task. Textual CBR (TCBR) is an emerging line that aims to apply CBR techniques on cases represented as textual descriptions. Similarity of cases is based on the similarity between their constituting features. Conventional CBR benefits from employing domain specific knowledge for similarity assessment. Correspondingly, TCBR needs to involve higher-order relationships between features, hence domain specific knowledge. In addition, the term order has also been contended to influence the similarity assessment. This paper presents an account where features and cases are represented using a distributed representation paradigm that captures higher-order relations among features as well as term order information.