Call for Service : Characterizing and Modeling Police Response to Serviceable Requests on Facebook

India is going digital in a big way; from banking to manufacturing to agriculture, each field is seeing the penetration of technology. Police organizations also have started using technology for effective policing. Most police organisations now have an official website, a Facebook page and a Twitter handle. Police not only use these new media services to showcase their organisation but also to interact with citizens very regularly. Police posts on Facebook or tweets on Twitter include a variety of topics ranging from traffic advisories, to awareness creation to bragging about their achievements. Similarly, the growing technology savvy population of India is using these mediums to share their grievances, concerns, etc. with the police. With a handful of police officers serving 1.25 billion people, it is no surprise that a lot of posts/tweets by the citizens go unnoticed by the police. Even features like tagging police commissioners and police accounts do not always yield the expected response, causing a sense of resentment. The police too find themselves helpless given the multitude of things.

With our continued interest in empowering police organizations with technology which can help them in their day-to-day activities, we have been working in the space of online social media and policing for some time now. For our research publications in this space, please visit here. For effective communication between the citizens and police, it is necessary for the police to understand the vast amount of content generated on their social media accounts. In this direction, we started thinking about how to break up the content into important versus unimportant, urgent versus non-urgent, etc. Our main aim in this research was to help police identify ‘serviceable’ content which can be served quickly and efficiently. Requests to which police should respond, evaluate or take action are considered as serviceable requests.  

We analyzed 85 official Facebook pages of police organizations in India and studied the nature of posts that citizens share on police Facebook pages. Not all posts require the same amount of attention from the police, there are some cases where immediate action needs to be taken while some can wait. Based on this analysis, we came up with six textual attributes that can identify serviceable posts; posts that need some kind of police response. We find such posts are marked by high negative emotions, more factual, and objective content such as location and time of incidences.

We identify four types of response that citizens may get on their posts:

(a) Forward: Posts which had enough information and could be forwarded to appropriate authorities for action. For instance, a resident posted, Date : 4/11/2015 (Wednesday), Time : 10:17 pm, Number : [withheld], Location : [withheld], Violations : Crossing line by way too much obstructing the vehicles which were coming from [withheld] entrance later he jumped the signal ……..

(b) Give Solution: Posts mostly included queries by residents to police that could be answered without any detail; resident asks, Admin !! Can U Explain to Me How Two Challans On Same Date Same Time in Just 5 Minutes Gap !! How Its Possible ?? Any Thing Wrong ??

(c) Acknowledge with thanks: Posts to which the police wrote “thanks for sharing the information” or “thanks for the appreciation.” For instance, resident remarks, Chennai City Traffic Police a humble salute from a fellow Chennaiite for the commendable job in such rains!!

(d) Need more details: In these resident’s posts, police inquired more details so that action could be taken, e.g., a resident asks, Cops driving wrong side [of road] near XXX hotel .. what action will be taken against them ? This post lacks information such as time and date when the incident happened.

To enhance response to serviceable posts, we propose a request – response identification framework. The approach followed in the paper is shown below:


Understanding Requests from Citizens:

Residents often use different language styles in posts while expressing their concerns and asking queries to police. Our approach includes following six category of features to characterize serviceable posts:Emotional Attributes,Cognitive and Interpersonal Attributes, Linguistic Attributes, Question Asking Attributes, Entity-Based Attributes, and Topical Attributes. These include the both handcrafted features and LDA / NMF based features that help automatically discover the latent dimensions and induce semantic features in our data.

Our analysis shows some intriguing results:

Serviceable requests show significantly higher value of negative emotional states i.e. “anger” (+15.38%), “disgust” (+47.8%), “fear” (+60%), and “sadness” (+10%) in comparison to non-serviceable requests. Most frequent topic is includes queries / question posed to police (Complaints represents complaints against cops in- correct decisions).

Comparing serviceable sub-types, we observe that 93.10% posts in Thanks sub-type did not receive a response from police. Posts in Forward sub-type received the maximum number of responses from police (63.6%, 182 posts). Table 1 below summarizes the number of posts that did not receive police responses.

Table 1: Number of posts that received responses (N of Events) and censored event showing posts that did not get response from the police.

Automated Classifier for Serviceability:

Our work explores a series of statistical models to predict serviceable posts and its different types. The model makes use of the content based measures – emotions, cognitive attributes, linguistic, question posed, entity and topical attributes. We explore five different classification algorithms – Random Forest (RF), Logistic Regression (LR), Decision Trees (DT), Adaptive Boosted Decision Trees (ADT), and Gradient Boosting Classifier (GBC) using balanced class weights. Table 2 below reports the performance of different algorithms to correctly identify serviceable posts.

Table 2: Mean Performance after 10-fold CV of different algorithms to correctly identify serviceable posts.

Through our work, we believe technological interventions can help increase the interactions between police and citizens and thereby increase the trust people have on police. The police too may have a more directed and cost-labour efficient mechanism in dealing with any law and order situation reported on their Facebook page. This will increase the overall well-being and safety of society.

Link to the analysis portal

Link to the accounts portal:

Full citation & link to the paper: Sachdeva, N., and Kumaraguru, P. Call for Service: Characterizing and Modeling Police Response to Serviceable Requests on Facebook. Accepted at the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW), 2017. PDF





A pleasant visit to Phoenix: Dg.o 2015

It was almost three years into PhD when we (Dr. PK and I) decided that I am going to work on understanding “how police use online social networks to connect with citizens.” This problem seemed interesting to us because it was about most overworked and sometimes unappreciated police officers in India. But then I did not realise that the problem would be of so much interest to the computer science community. In January 2015, we submitted our first paper analysing Bangalore city police Facebook page to Digital Government 2015. It was morning of March 16th when we got the paper acceptance notification. I was thrilled, excited, satisfied and extremely happy to read the reviews. We were nominated for “best paper award.”

The conference was is Phoenix, Arizona in the month of May, 2015. We had plenty of time to prepare for the conference. Thankfully, I got the Visa and TCS funding to travel to USA. Then within few days came the day of travel (26 May 2015). When I was at the airport, I was reminded of my last US visit. I missed my advisor and friends who come to drop me at the airport last time. But I knew they wished the best to happen with me on this trip. I comfortably reached Phoenix and got a extremely comfortable room to stay at Taylor’s Place (just 3 minutes away from the conference venue). I was so excited to be at the conference that without any delay after I landed, I went for the workshop.

This workshop was about Data, Tools, & Innovation: Trending Applications in US Cities organised by Karen Mossberger, Arizona State University, and Kellen Gracey, University of Iowa. I got to learn about how broadband had penetrated in the community across several years. This is a rare data set to get and had taken almost an year for Dr Mossberger and her team to get access to it. It helped me understand various factors that influence the internet penetration and how the world’s most developed country deals with ethnicity challenges to make it citizens technology enabled. Workshop also introduced me to visualization that was designed for community decision-making using technology from ASU’s Decision Theatre network. Some of these were interesting simulations which helped decision makers to better understand disaster situations. After this amazing session I came back to my room all excited for the next when the conference sessions started. Back in the room, I met Sabrina Scherer, my roommate for the next few days. Her presence made my evenings memorable and fulfilled. This marked the end of Day 1.

Day 2: The best part of the conference was participants getting to meet police officers, CIOs, Disaster managers who are otherwise so difficult to meet. I am sure it would have taken lot of planning to conduct such engaging panel discussions. The first one was regarding body cameras used by the police officers on duty. The workshop ended with a message that a strong leadership can help in technology adoption. It was interesting to hear the courts view also and how cameras had helped save officers from false allegations. But something that I was neither able to agree nor disagree to was that videos captured could bias the opinion of the investigating officer, they could make a story based on the video. Also, how these hours and hours of videos are increasing work load rather than being useful. Thus resulting in a unique and challenging bigdata problem where police needs technologists’ help.

In Day 2, In the evening, I had to present my poster. I reached there at 5 and was all set with my poster. The volunteers were extremely generous and helped me setup the poster. While I was waiting for the poster session to start, a gentleman came and asked we about my poster. I explained my work and the gentleman seemed quite impressed with it, minutes later I realised that he was Bob Worsley, Arizona State Senator. It was interesting to see the amount of importance and emphasis he gave to citizen involvement in governance. His view that “governments do everything they are supposed to do except listening to what citizens want” correctly explained the need for governments to engage with citizens. He introduced his initiative to involve with citizens. It was satisfying to see that people involved in governance consider citizen engagement as important as we do in collaborative research. This was followed by opening of poster session, I was delighted to get great response for my work. Content and satisfied that I was doing useful work, I went back to my room. Next day, was going to a big day as it was my first ever international conference talk.

Day 3: I took a while to decide what would be the best dress to wear for my first conference talk ever. And then with some time going into preparation for my presentation, I realised that it was already 10 AM. I had missed the morning discussion session :(. I went to the conference hall attended the next session but even while the session was on I was thinking about my presentation. Finally it was time for me to present our paper. I was all set for the questions. After the presentation, a question was, is police even aware of this work that they could make use of it. That moment, I felt so blessed that Dr. PK gives so much emphasis on making our work visible to actual stakeholders. Because of his interest, I could confidently answer that yes, Police department are aware of our study and we work with them when ever an opportunity is there.

Finally all the sessions came to an end. After this we went to the Heard Museum for Awards Dinner. It was an interesting place where I got to learn about American Indians. They had so similar concepts like tribes in India. This was followed by a talk from Dr. Traci Morris, Director of the American Indian Policy Institute. And then came the time for award ceremony, since I had got such a positive response for the poster, I was expecting a best poster award. As the award was announced, I was a little disappointed and wanted to go back to room as soon as possible. However, the best paper awards was still to be announced. I had completely forgotten that our paper was also nominated by now and was waiting to rush back to my room. The program chairs first explained how the best paper was decided and said that since they did not have many short papers they are giving two best paper awards. They announced one best paper award and then their was some suspense. Finally, the final Best paper was announced and I heard our names being called. This was more than I could ask for. I was extremely excited to receive that award and was so thankful to the reviewers who liked our paper and appreciated it so much. As appreciation, conference organisers also gave us a cheque of $400 🙂

I have been involved in multiple research projects but somehow this thread is getting closure to what I would have liked to be part of during my Ph.D. life. Thanks to my advisor for giving me this opportunity and keeping faith in the work I did.