Ph. D. Thesis defense: Niharika Sachdeva
- Who: Niharika Sachdeva
- What: Precog's third Ph.D. thesis defense
- When: 1530 - 1630hrs IST, July 27, 2017
- Where: Board room, Fifth floor, IIIT-Delhi
- Why: Precogs put in a lot of effort in their work, you don't want to miss seeing it.
- Facebook LIVE: https://www.facebook.com/ponnurangam.kumaraguru/
- Title: Social Media and Policing: Computational Approaches to Enhancing Collaborative Action between Residents and Law Enforcement.
- Abstract: Law and order concerns are one of the major disquiets of urban societies in day-to-day life. Various crime prevention theories show the importance of collaboration between residents and police for maintaining law and order and addressing concerns. Collaborative action across public organizations such as police shows different challenges like enabling collective action, problem-solving, accountability, and responsiveness of the organizational actors towards residents. To enable collective action and problem solving with the help of residents, modern police departments explore innovative mechanisms to overcome the barrier of reachability and communication. Using these mechanisms, residents can convey their concerns and enquire/provide information useful for police contributing towards the collaborative process. With growing reach of web 2.0, social media has emerged as an effective platform to enable collaboration between police and resident. Social media use for communication between police and resident introduces various challenges for organizations. Owing to the massive volume of content on social media, the responsiveness of the police to the online content determine the overall success of the collaborative efforts. Additionally, social media raises challenges such as inferring actionable information and quantifying behavior (like emotions and other linguistic attributes) from unconstrained natural language text. Police organizations seek the support of technology and automation to address these challenges. Several researchers have examined the efficacy of collaborating through social media in a diverse set of scenarios like crises (natural and man-made) and socio-political upheavals. Despite its usefulness in crises, social media role to enable police in collective action and responding to day-to-day concerns of residents remains largely unexplored.
Therefore, we believe it is important to understand, analyze and enhance the opportunity for collaboration between police and residents using day-to-day life using social media. In this thesis, we study collaborative efforts by police on social media in the specific context of India. The policing department in India has only 130 personnel per 100,000 residents which is much lower than the UN recommended 270–280 personnel per 100,000 residents [35, 82]. Given the constraint on number of officers, police in India have felt the need to obtain community based collaboration to accomplish its increasingly vast duties [35]. Social media popularity among residents has motivated the police to use it for day-to-day interactions and improved community policing. Based on this understanding, we define the core research question of this thesis as how can a platform such as social media be utilized to support, analyze, and enhance collaborative action by police organization and residents ? This thesis makes following contributions towards the core research question: a) Investigate the current role of social media in supporting police and residents’ collaboration for community policing and collective action, b) Mine and quantify unstructured data on social media for managing actionable information and understanding societal beliefs affecting day-to-day policing for improved collective action, and c) Develop a framework for extracting “serviceable requests” from social media to enhance engagement among residents and predicting expected police response to such requests.
To answer the first research question of this thesis, we conduct semi-structured interviews and surveys of both the stake-holders(police and residents) to understand social media usage requirements. Through our analysis, we highlight residents and police thoughts about information shared, need for measures to handle offensive comments, and acknowledgment overload for police on social media. Following this, we adopt a mixed method approach (qualitatively and quantitatively analysis) for analyzing the content generated on police profiles on social media. We perform this analysis along multiple dimensions: content attributes, meta-data (likes and comments), image attributes, and police response time. Our results show that residents post information (e.g., location) about various crimes such as neighborhood issues, financial frauds, and thefts. Police response to residents’ post varies from ‘reply’, ‘acknowledge’, ‘follow-up’, and ‘ignore’. We demonstrate that using statistical, unsupervised, and bag-of-words LIWC methods; we can quantify interaction patterns / cues and translate them into features that can be helpful for developing frameworks to corroborate collective intelligence. We also present a real-time image search system using Convolution Neural Networks(CNN) which retrieves modified images that allow first responders such as police to analyze the current spread of images, sentiments floating, and details of users propagating such content. The system aids officials to save the time of manually analyzing the content as it reduces the search space on an average by 67%. Finally, towards our third research goal, this thesis proposes a request–response detection framework for identifying resident’s posts that elicit police response (called serviceable posts), based on the input of police experts. Our observations show a decrease in police response time of the serviceable requests that can be immediately resolved, thus suggesting that successful identification of serviceable posts may ultimately result in systems that facilitate in extending timely police support and improve police responsiveness towards residents. Lastly, we evaluate a series of statistical models to predict serviceable posts and its different types.
Ph. D. Thesis defense: Paridhi Jain
- Who: Paridhi Jain
- What: Precog's second Ph.D. thesis defense
- When: 1730 - 1900hrs IST, April 25, 2016
- Where: Board room, Fifth floor, IIIT-Delhi
- Why: Precogs put in a lot of effort in their work, you don't want to miss seeing it.
- Facebook event: https://www.facebook.com/events/1523107397999127/
- Title: Automated Methods for Identity Resolution across Online Social Networks
- Abstract: Today, more than two hundred Online Social Networks (OSNs)
exist where each OSN extends to offer distinct services to its users
such as eased access to news or better business opportunities. To
enjoy each distinct service, a user innocuously registers herself on
multiple OSNs. For each OSN, she defines her identity with a different
set of attributes, genre of content and friends to suit the purpose of
using that OSN. Thus, the quality, quantity and veracity of the
identity varies with the OSN. This results in dissimilar identities of
the same user, scattered across Internet, with no explicit links
directing to one another. These disparate unlinked identities worry
various stakeholders. For instance, security practitioners find it
difficult to verify attributes across unlinked identities; enterprises
fail to create a holistic overview of their customers.
Research that finds and links disconnected identities of a user across
OSNs is termed as identity resolution. Accessibility to unique and
private attributes of a user like ‘email’ makes the task trivial,
however in absence of such attributes, identity resolution is
challenging. In this dissertation, we make an effort to leverage
intelligent cues and patterns extracted from partially overlapping
list of public attributes of compared identities. These patterns
emerge due to consistent user behavior like sharing same mobile
number, content or profile picture across OSNs. Translating these
patterns into features, we devise novel heuristic, unsupervised and
supervised frameworks to search and link user identities across social
networks. Proposed search methods use an exhaustive set of public
attributes looking for consistent behavior patterns and fetch correct
identity of the searched user in the candidate set for an additional
11% users. An improvement on the proposed search mechanisms further
optimizes time and space complexity. Suggested linking method compares
past attribute value sets and correctly connect identities of an
additional 48% users, earlier missed by literature methods that
compare only current values. Evaluations on popular OSNs like Twitter,
Instagram and Facebook prove significance and generalizability of the
linking method.
Proposed search and linking methods are applicable to users that
exhibit evolutionary and consistent behavior on OSNs. To understand
the dynamics and reasons for such behavior, we conduct two independent
in-depth studies. For user evolutionary behavior, specifically for
username, we observe that username evolution leads to broken link (404
page) to a user profile. Yet, 10% of 8.7 million tracked Twitter users
changed their username in two months. Investigation reveals that
reasons to change include malign intentions like fraudulent username
promotion and benign ones like express support to events. We believe
that Twitter can monitor frequent username changes, derive malign
intentions and suspend accounts if needed. Study of sharing
information consistently across OSNs, e.g. mobile number, highlights
why users share a personally identifiable information online and how
can it be used with auxiliary information sources to derive details of
a user.
In summary, this dissertation encashes previously unused public user
information available on a social network for identity resolution via
novel methods. The thesis work makes following advancements: a)
Propose search frameworks that aim to fetch correct identity of a user
in the candidate set by searching with public and discriminative
attributes, b) Propose a supervised classification framework for
linking identities that compares respective attribute histories in
situations where state-of-the-art methods fail to predict the link, c)
Study username evolution on Twitter, and d) Study mobile number
sharing behavior across OSNs. Proposed methods require no user
authorization for data access, yet successfully leverage innocuous
user public activity and details, find her accounts across OSNs and
help stakeholders with better insights on user’s likings or her
suspicious intentions.
Masters Thesis defense: Sonal Goel
- Who: Sonal Goel
- What: Masters thesis defense
- When: 1600 - 1730 hrs IST, April 25, 2016
- Where: Board room, Fifth floor, IIIT-Delhi
- Why: Precogs put in a lot of effort in their work, you don't want to miss seeing it.
- Title: Image Search for Improved Law and Order: Search, Analyze, Predict image spread on Twitter.
- Abstract: Social media is often used to spread images that can instigate anger among people, hurt their religious, political, caste, and other sentiments, this in return can create law and order situation in society. This results the need for law enforcement agencies to inspect the spread of images related to such events on social media in real time. To help the law enforcement agencies to analyse the image spread on microblogging websites, we developed an Open Source Real Time Image search system, where the user can give an image, and a supportive text related to image and the system finds the images that are similar to the input image and their count. The system proposed is robust to identify images that can be cropped, scaled (to a certain factor), images with text embedded, images stitched with other images, images with varied brightness, and some combination of all these. On the input text, the system runs a text mining algorithm to extract the keywords, retrieve images related to these keywords from Twitter, and use Image comparison methodology to extract similar images. The system can analyse the users who were propagating the content, the sentiments floating with them, and their retweet analysis. We found that Improved ORB (ORB + RANSAC) performs the best for image similarity and using it we are able to achieve an accuracy of above 85% in all the cases tested. The system developed is being used in one of the Government security agency. In addition to identifying the similar images, we also aim to predict the influence of such events on people as diffusion rate. In microblogging sites like Twitter, information provided by tweets diffuses over the users through retweets. Hence, to further enhance the understanding and controlling the diffusion of these kinds of images, we focus to predict the retweet count of such images by using visual cues from the images, content based information and structure-based features. For this, we build a random forest regression model that takes some tweet, image and structural features to predict the retweet count.
Masters Thesis defense: Pradyumn Nand
- Who: Pradyumn Nand
- What: Masters thesis defense
- When: 1100 - 1230 hrs IST, April 29, 2016
- Where: Board room, Fifth floor, IIIT-Delhi
- Why: Precogs put in a lot of effort in their work, you don't want to miss seeing it.
|