http://repository.iiitd.edu.in/xmlui/handle/123456789/6 2026-04-11T11:24:12Z 2026-04-11T11:24:12Z Asthana, Siddhartha Singh, Pushpendra Singh, Amarjeet Naik, Vinayak http://repository.iiitd.edu.in/xmlui/handle/123456789/29 2017-07-24T17:14:01Z 2012-03-26T10:39:51Z

Context-aware IVR : challenges and opportunities Asthana, Siddhartha; Singh, Pushpendra; Singh, Amarjeet; Naik, Vinayak Voice based telecommunication services are emerging as most appropriate medium for information dissemination in developing regions, as they overcome prevalent low literacy rate and are more reachable than any other medium like internet. However, present-day Interactive Voice Response (IVR) systems are not able to capture user requirements and present a rigid interface to its users, and thus the IVR systems are commonly considered as frustrating to use. In this paper, we are proposing an architecture to build context-aware IVR systems, which can adapt themselves to match user requirements and provide a better experience, thus enabling their widespread use. We did a real world deployment to understand the requirements for the new architecture. We intend to make use of work in context-aware systems and adaptive systems to create next-generation IVR systems that have humanlike ability in tackling caller intricacies with ease of access like internet.

2012-03-26T10:39:51Z Sureka, Ashish http://repository.iiitd.edu.in/xmlui/handle/123456789/28 2017-07-24T17:14:28Z 2012-03-26T10:33:35Z

140 characters of @hate and #protest Sureka, Ashish Research shows that cyber-hate, illegal or malicious form of cyber-protest and cyber-activism in online social media and Web 2.0 platforms has become a common phenomenon. This is a growing concern and hence automated techniques to counter such forms of online propaganda and identification of users and virtual communities is an area which has recently attracted a lot of research attention. In this paper, we present a simple and effective method to mine Twitter (a very popular and largest micro-blogging service) data for automatically identifying users and communities having a shared agenda. We propose a generic framework that consists of a systematic and focused traversal of the follower-network on Twitter and a user profile classifier based on contentbased features. We customize the proposed framework for a specific domain and demonstrate that the proposed approach is effective. We perform empirical analysis on data crawled from Twitter and the experimental results on the test dataset reveals that the proposed features and framework can successfully identify twitterers and hidden communities having a common agenda or shared interest.

2012-03-26T10:33:35Z Bhatt, Himanshu S Bharadwaj, Samarth Singh, Richa Vatsa, Mayank http://repository.iiitd.edu.in/xmlui/handle/123456789/27 2017-07-24T17:13:55Z 2012-03-26T10:26:22Z

Memetic approach for matching sketches with digital face images Bhatt, Himanshu S; Bharadwaj, Samarth; Singh, Richa; Vatsa, Mayank One of the important cues in solving crimes and apprehending criminals is matching sketches with digital face images. This paper presents an automated algorithm that extracts discriminating information from local regions of both sketches and digital face images. Structural information along with the minute details present in local facial regions are encoded using multi-scale circular Weber’s Local descriptor. Further, an evolutionary memetic optimization is proposed to assign optimal weights to every local facial region to boost the identification performance. Since, forensic sketches or digital face images can be of poor quality, a pre-processing technique is used to enhance the quality of images and improve the identification performance. Comprehensive experimental evaluation on different sketch databases show that the proposed algorithm yields better identification performance compared to existing algorithms and two commercial face recognition systems.

2012-03-26T10:26:22Z Gupta, Aditi Kumaraguru, Ponnurangam http://repository.iiitd.edu.in/xmlui/handle/123456789/26 2017-07-24T17:14:54Z 2012-03-26T10:19:46Z

Twitter explodes with activity in mumbai blasts! a lifeline or an unmonitored daemon in the lurking? Gupta, Aditi; Kumaraguru, Ponnurangam Online social media has become an integral part of every Internet users' life. It has given common people a platform and forum to share information, post their opinions and promote campaigns. The threat of exploitation of social media like Facebook, Twitter, etc. by malicious entities, becomes crucial during a crisis situation, like bomb blasts or natural calamities such as earthquakes and floods. In this report, we attempt to characterize and extract patterns of activity of general users on Twitter during a crisis situation. This is the fi rst attempt to study an India-centric crisis event such as the triple bomb blasts in Mumbai (India), using online social media. In this research, we perform content and activity analysis of content posted on Twitter after the bomb blasts. Through our analysis, we conclude, that the number of URLs and @mentions in tweets increase during the time of the crisis in comparison to what researchers have exhibited for normal circumstances. In addition to the above, we empirically show that the number of tweets or updates by authority users (those with large number of followers) are very less, i.e. majority of content generated on Twitter during the crisis comes from non authority users. In the end, we discuss certain case scenarios during the Mumbai blasts, where rumors were spread through the network of Twitter.

2012-03-26T10:19:46Z