Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284293
Mihir Wadwekar, Kishore Kothapalli
Finding the articulation points and the biconnected components of an undirected graph has been a problem of huge interest in graph theory. Over the years, several sequential and parallel algorithms have been presented for this problem. Our paper here presents and implements a fast parallel algorithm on GPU which is to the best of our knowledge the first such attempt and also the fastest implementation across architectures. The implementation is on an average 4x faster then the next best implementation. We also apply an edge-pruning technique which results in a further 2x speedup for dense graphs.
{"title":"A fast GPU algorithm for biconnected components","authors":"Mihir Wadwekar, Kishore Kothapalli","doi":"10.1109/IC3.2017.8284293","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284293","url":null,"abstract":"Finding the articulation points and the biconnected components of an undirected graph has been a problem of huge interest in graph theory. Over the years, several sequential and parallel algorithms have been presented for this problem. Our paper here presents and implements a fast parallel algorithm on GPU which is to the best of our knowledge the first such attempt and also the fastest implementation across architectures. The implementation is on an average 4x faster then the next best implementation. We also apply an edge-pruning technique which results in a further 2x speedup for dense graphs.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121742645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284328
Sakshi Bansal, Chetna Gupta, Adwitiya Sinha
The widespread eminence of internetworking plays a vital role in revolutionizing the commercial domain. Prior to make purchases, people spend a lot of time on the internet to gather information and feedback, so as to better direct their decisions. Since, customers are not present in person in the stores they can easily shift from one supplier to the other via online portals. From business point of view, this could be harmful for the profit and propaganda of traders. In this research, the prime focus is to overcome such problems confronted by trading industries. Our proposed model analyses ‘Clickstream Events’ of online users along with set of contextual details for providing better recommendations. Recording the behavior of several users can help industries to discover habits and tendencies of user, which can lead to even better and effective decisions to improve business profit and its market coverage. Further, our proposed model aims at discovering the relationship between various items, from the context of user interest. Market Basket Analysis is performed that assists the user with appropriate options while purchasing products along with items already purchased, thereby offering better buying experience.
{"title":"Clickstream & behavioral analysis with context awareness for e-commercial applications","authors":"Sakshi Bansal, Chetna Gupta, Adwitiya Sinha","doi":"10.1109/IC3.2017.8284328","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284328","url":null,"abstract":"The widespread eminence of internetworking plays a vital role in revolutionizing the commercial domain. Prior to make purchases, people spend a lot of time on the internet to gather information and feedback, so as to better direct their decisions. Since, customers are not present in person in the stores they can easily shift from one supplier to the other via online portals. From business point of view, this could be harmful for the profit and propaganda of traders. In this research, the prime focus is to overcome such problems confronted by trading industries. Our proposed model analyses ‘Clickstream Events’ of online users along with set of contextual details for providing better recommendations. Recording the behavior of several users can help industries to discover habits and tendencies of user, which can lead to even better and effective decisions to improve business profit and its market coverage. Further, our proposed model aims at discovering the relationship between various items, from the context of user interest. Market Basket Analysis is performed that assists the user with appropriate options while purchasing products along with items already purchased, thereby offering better buying experience.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114306601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284287
Mahak Gambhir, Kishore Kothapalli
A dominating set of a small size is useful in several settings including wireless networks, document summarization, secure system design, and the like. In this paper, we start by studying three distributed algorithms that produce a small sized dominating sets in a few rounds. We interpret these algorithms in the natural shared memory setting and experiment with these algorithms on a multi-core CPU. Based on the observations from these experimental results, we propose variations to the three algorithms and also show how the proposed variations offer interesting trade-offs with respect to the size of the dominating set produced and the time taken.
{"title":"A study on the minimum dominating set problem approximation in parallel","authors":"Mahak Gambhir, Kishore Kothapalli","doi":"10.1109/IC3.2017.8284287","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284287","url":null,"abstract":"A dominating set of a small size is useful in several settings including wireless networks, document summarization, secure system design, and the like. In this paper, we start by studying three distributed algorithms that produce a small sized dominating sets in a few rounds. We interpret these algorithms in the natural shared memory setting and experiment with these algorithms on a multi-core CPU. Based on the observations from these experimental results, we propose variations to the three algorithms and also show how the proposed variations offer interesting trade-offs with respect to the size of the dominating set produced and the time taken.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126855198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284332
Abhinav Tomar, P. K. Jana
Mobile charging is an important topic for wireless rechargeable sensor networks (WRSNs) which has been studied extensively over the past few years. With the help of wireless energy transfer (WET), it is now possible to extend lifetime of sensor nodes to a longer period. In WET, wireless charging vehicle (WCV) moves on its designed traveling path in the network and charges sensor nodes by halting at some stopping locations. However, large scale WRSNs demand for multiple WCVs to make mobile charging more feasible. It is to be noted that for designing energy efficient traveling paths, it is desirable to minimize the stopping locations of the WCV which improves charging efficiency in the noticeable amount. Moreover, charging multiple nodes at the same time improves charging performance and thus it is recent trend. Inspired by the above facts, in this paper, we serve the objective of designing energy efficient traveling paths for multiple WCVs with multi-node charging. Our proposed scheme works in two phases. In the first phase, we perform clustering to divide the network region into charging subregions according to available number of WCVs. In the second phase, we apply charging radius based nearest neighbor approach (CR-NN) to find anchor points (i.e., stopping locations) for those WCVs to design traveling paths. The simulation results confirm the effectiveness of our scheme and demonstrate performance gains with respect to several metrics such as charging latency, waiting time, node failure rate, and so on.
{"title":"Designing energy efficient traveling paths for multiple mobile chargers in wireless rechargeable sensor networks","authors":"Abhinav Tomar, P. K. Jana","doi":"10.1109/IC3.2017.8284332","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284332","url":null,"abstract":"Mobile charging is an important topic for wireless rechargeable sensor networks (WRSNs) which has been studied extensively over the past few years. With the help of wireless energy transfer (WET), it is now possible to extend lifetime of sensor nodes to a longer period. In WET, wireless charging vehicle (WCV) moves on its designed traveling path in the network and charges sensor nodes by halting at some stopping locations. However, large scale WRSNs demand for multiple WCVs to make mobile charging more feasible. It is to be noted that for designing energy efficient traveling paths, it is desirable to minimize the stopping locations of the WCV which improves charging efficiency in the noticeable amount. Moreover, charging multiple nodes at the same time improves charging performance and thus it is recent trend. Inspired by the above facts, in this paper, we serve the objective of designing energy efficient traveling paths for multiple WCVs with multi-node charging. Our proposed scheme works in two phases. In the first phase, we perform clustering to divide the network region into charging subregions according to available number of WCVs. In the second phase, we apply charging radius based nearest neighbor approach (CR-NN) to find anchor points (i.e., stopping locations) for those WCVs to design traveling paths. The simulation results confirm the effectiveness of our scheme and demonstrate performance gains with respect to several metrics such as charging latency, waiting time, node failure rate, and so on.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133348070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284320
Shalini, Sanjay Kumar Jain
In present scenario, extracting global frequent itemsets from big data, distributed across multiple data streams, with its real time requirements is a complex problem. In this article, we propose an algorithm that reduces number of local frequent itemsets communicated to root node to extract global patterns from distributed multiple data streams. Here, the algorithm sends only local frequent itemsets to the root node instead of sending summary of local data streams. We compress sets of local frequent itemsets and send them to the root node using algorithm called Frequent Itemset Reduction (FIR) algorithm. We present two indexing structures known as I-list and Modified Seg-tree (MsegT) to store all local frequent itemsets at root node. Our experimental study exhibits that the FIR algorithm reduces communication cost in a good extent and MsegT produces substantial good results compared to I-list and few state-of-the-art techniques.
{"title":"A frequent itemset reduction algorithm for global pattern mining on distributed data streams","authors":"Shalini, Sanjay Kumar Jain","doi":"10.1109/IC3.2017.8284320","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284320","url":null,"abstract":"In present scenario, extracting global frequent itemsets from big data, distributed across multiple data streams, with its real time requirements is a complex problem. In this article, we propose an algorithm that reduces number of local frequent itemsets communicated to root node to extract global patterns from distributed multiple data streams. Here, the algorithm sends only local frequent itemsets to the root node instead of sending summary of local data streams. We compress sets of local frequent itemsets and send them to the root node using algorithm called Frequent Itemset Reduction (FIR) algorithm. We present two indexing structures known as I-list and Modified Seg-tree (MsegT) to store all local frequent itemsets at root node. Our experimental study exhibits that the FIR algorithm reduces communication cost in a good extent and MsegT produces substantial good results compared to I-list and few state-of-the-art techniques.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132230189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284325
Ankit Tripathi, Benu Changmai, Shrukul Habib, Nagaratna B. Chittaragi, S. Koolagudi
Video synchronization is the task of content-based alignment of two or more videos depicting the same event with spatial variations or in the same object with temporal changes. Video synchronization is one of the most fundamental tasks when it comes to manipulations with temporally or spatially multi-perspective video-shots. In this paper, a model is proposed to deal with the synchronization problem and efficiently tackles issues arising during synchronizing two videos. Here, videos are dealt, at the frame level with features from each frame forming the basis of alignment. Features are matched and mapped to generate a cost matrix of similarities among the frames of the videos in concern. A modified version of Djikstra's algorithm that yields an optimal path through the matrix is applied. Through an optimal path, events are grouped into adjacent regions following which temporal warpings are introduced into the videos to achieve the best possible alignment among them. The model has proven to be efficient and compatible with all classes of quality levels of videos.
{"title":"Normalized videosnapping: A non-linear video synchronization approach","authors":"Ankit Tripathi, Benu Changmai, Shrukul Habib, Nagaratna B. Chittaragi, S. Koolagudi","doi":"10.1109/IC3.2017.8284325","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284325","url":null,"abstract":"Video synchronization is the task of content-based alignment of two or more videos depicting the same event with spatial variations or in the same object with temporal changes. Video synchronization is one of the most fundamental tasks when it comes to manipulations with temporally or spatially multi-perspective video-shots. In this paper, a model is proposed to deal with the synchronization problem and efficiently tackles issues arising during synchronizing two videos. Here, videos are dealt, at the frame level with features from each frame forming the basis of alignment. Features are matched and mapped to generate a cost matrix of similarities among the frames of the videos in concern. A modified version of Djikstra's algorithm that yields an optimal path through the matrix is applied. Through an optimal path, events are grouped into adjacent regions following which temporal warpings are introduced into the videos to achieve the best possible alignment among them. The model has proven to be efficient and compatible with all classes of quality levels of videos.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127247242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284308
Richa Sharma, A. Sureka
Crowdsourcing has aroused a lot of interest in Requirements Engineering (RE) research community. RE activities are inherently complex in nature — both effort and time intensive, and quite dependent on each-other. The potential of crowdsourcing has been acknowledged for addressing complex tasks in general. We intend to study the potential of crowdsourcing for a broad spectrum of RE activities, i.e. from gathering requirements to their validation, through our proposed tool, CRUISE (Crowdsourcing for Requirements Engineering). CRUISE is aimed at involving interested users for gathering, analysing, validating, prioritizing, and negotiating requirements. In this paper, we present our vision and future roadmap for our proposed tool, CRUISE. We also report our observations from preliminary investigation experimental study to check the feasibility and viability of crowdsourcing based tool for Requirements Elicitation activity.
{"title":"CRUISE: A platform for crowdsourcing Requirements Elicitation and evolution","authors":"Richa Sharma, A. Sureka","doi":"10.1109/IC3.2017.8284308","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284308","url":null,"abstract":"Crowdsourcing has aroused a lot of interest in Requirements Engineering (RE) research community. RE activities are inherently complex in nature — both effort and time intensive, and quite dependent on each-other. The potential of crowdsourcing has been acknowledged for addressing complex tasks in general. We intend to study the potential of crowdsourcing for a broad spectrum of RE activities, i.e. from gathering requirements to their validation, through our proposed tool, CRUISE (Crowdsourcing for Requirements Engineering). CRUISE is aimed at involving interested users for gathering, analysing, validating, prioritizing, and negotiating requirements. In this paper, we present our vision and future roadmap for our proposed tool, CRUISE. We also report our observations from preliminary investigation experimental study to check the feasibility and viability of crowdsourcing based tool for Requirements Elicitation activity.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"18 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121030582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284305
Raju Pal, M. Saraswat
Data clustering is one of the important tool in data analysis which partitions the dataset into different groups based on similarity and dissimilarity measures. Clustering is still a NP-hard problem for large dataset due to the presence of irrelevant, overlapping, missing and unknown features which leads to converge it into local optima. Therefore, this paper introduces a novel hybrid meta-heuristic data clustering approach which is based on K-means and biogeography-based optimization (BBO). The proposed method uses K-means to initialize the population of BBO. The simulation has been done on eleven dataset. Experimental and statistical results validate that proposed method outperforms the existing methods.
{"title":"Data clustering using enhanced biogeography-based optimization","authors":"Raju Pal, M. Saraswat","doi":"10.1109/IC3.2017.8284305","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284305","url":null,"abstract":"Data clustering is one of the important tool in data analysis which partitions the dataset into different groups based on similarity and dissimilarity measures. Clustering is still a NP-hard problem for large dataset due to the presence of irrelevant, overlapping, missing and unknown features which leads to converge it into local optima. Therefore, this paper introduces a novel hybrid meta-heuristic data clustering approach which is based on K-means and biogeography-based optimization (BBO). The proposed method uses K-means to initialize the population of BBO. The simulation has been done on eleven dataset. Experimental and statistical results validate that proposed method outperforms the existing methods.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128063251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284288
Harshit Gujral, Abhinav Sharma, S. Mittal
Searching in-file content is a crucial task in everyday computing, made particularly difficult due to lack of efficient in-file content search system in windows operating system. The goal of this paper is to present a cloud-based exhaustive in-file content search algorithm using three dimensional hash data structure. To facilitate an abundant size of hash and to save user's memory space we have used cloud for accommodating hash structure. We aim at presenting the user with required retrieval in the time complexity of O (constant), usually within 3–8 seconds. Our retrieval is a comprehensible combination of user's input string, the filename(s) containing it. Also, unlike windows operating system's search system, it permits to include location(s) and even multiple occurrences of user defined string inside a file.
{"title":"No-escape search: Design and implementation ofcloud based directory content search","authors":"Harshit Gujral, Abhinav Sharma, S. Mittal","doi":"10.1109/IC3.2017.8284288","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284288","url":null,"abstract":"Searching in-file content is a crucial task in everyday computing, made particularly difficult due to lack of efficient in-file content search system in windows operating system. The goal of this paper is to present a cloud-based exhaustive in-file content search algorithm using three dimensional hash data structure. To facilitate an abundant size of hash and to save user's memory space we have used cloud for accommodating hash structure. We aim at presenting the user with required retrieval in the time complexity of O (constant), usually within 3–8 seconds. Our retrieval is a comprehensible combination of user's input string, the filename(s) containing it. Also, unlike windows operating system's search system, it permits to include location(s) and even multiple occurrences of user defined string inside a file.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130521367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sarcasm is a nuanced form of communication where the individual states opposite of what is implied. One of the major challenges of sarcasm detection is its ambiguous nature. There is no prescribed definition of sarcasm. Another major challenge is the growing size of the languages. Every day hundreds of new slang words are being created and used on these sites. Hence, the existing corpus of positive and negative sentiments may not prove to be accurate in detecting sarcasm. Also, the recent developments in online social networks allow its users to use varied kind of emoticons with the text. These emoticons may change the polarity of the text and make it sarcastic. Due to these difficulties and the inherently tricky nature of sarcasm it is generally ignored during social network analysis. As a result the results of such analysis are affected adversely. Thus, sarcasm detection poses to be one of the most critical problems which we need to overcome. Detection of sarcastic content is vital to various NLP based systems such as text summarization and sentiment analysis. In this paper we address the problem of sarcasm detection by leveraging the most common expression of sarcasm — “positive sentiment attached to a negative situation”. Our work uses two ensemble based approaches — voted ensemble classifier and random forest classifier. Unlike current approaches to sarcasm detection which rely on existing corpus of positive and negative sentiments for training the classifiers, we use a seeding algorithm to generate training corpus. The proposed model also uses a pragmatic classifier to detect emoticon based sarcasm.
{"title":"Sarcasm detection of tweets: A comparative study","authors":"Tanya Jain, Nilesh Agrawal, Garima Goyal, Niyati Aggrawal","doi":"10.1109/IC3.2017.8284317","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284317","url":null,"abstract":"Sarcasm is a nuanced form of communication where the individual states opposite of what is implied. One of the major challenges of sarcasm detection is its ambiguous nature. There is no prescribed definition of sarcasm. Another major challenge is the growing size of the languages. Every day hundreds of new slang words are being created and used on these sites. Hence, the existing corpus of positive and negative sentiments may not prove to be accurate in detecting sarcasm. Also, the recent developments in online social networks allow its users to use varied kind of emoticons with the text. These emoticons may change the polarity of the text and make it sarcastic. Due to these difficulties and the inherently tricky nature of sarcasm it is generally ignored during social network analysis. As a result the results of such analysis are affected adversely. Thus, sarcasm detection poses to be one of the most critical problems which we need to overcome. Detection of sarcastic content is vital to various NLP based systems such as text summarization and sentiment analysis. In this paper we address the problem of sarcasm detection by leveraging the most common expression of sarcasm — “positive sentiment attached to a negative situation”. Our work uses two ensemble based approaches — voted ensemble classifier and random forest classifier. Unlike current approaches to sarcasm detection which rely on existing corpus of positive and negative sentiments for training the classifiers, we use a seeding algorithm to generate training corpus. The proposed model also uses a pragmatic classifier to detect emoticon based sarcasm.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114415517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：