Abstract

Massively Multiplayer Online Role-Playing Games (MMORPGs) are persistent virtual environments where millions of players interact in an online manner. We study the problem of player churn and social contagion using MMORPG game logs by analyzing the impact of a node’s churn behavior on its immediate neighborhood or group. The two key research questions in this paper are - When an active node, ego, becomes dormant, what is the impact on the activity behavior of ego’s immediate neighbor, alter, 1) based on ego’s characteristics and ego’s relationship with alter and 2) based on the activity behavior of alter’s remaining neighbors. We use a supervised learning framework to study the impact of player churn and social contagion. Experimental results show that the classification models perform substantially better than random for both the research problems. Finally, we use a data-driven approach to propose a player typology based on degree of socialization and analyze churn behavior among these player types. Experimental results show that the loner player type is much more likely to churn than the socializer player types and as the degree of socialization decreases among socializers, the propensity to churn increases. Index Terms—churn, social contagion, supervised learning, clustering, player typology

Abstract

Livestreaming platforms enable content producers, or streamers, to broadcast creative content to a potentially large viewer base. Chatrooms form an integral part of such platforms, enabling viewers to interact both with the streamer, and amongst themselves. Streams with high engagement (many viewers and active chatters) are typically considered engaging, and often promoted to end users by means of recommendation algorithms, and exposed to better monetization opportunities via revenue share from platform advertising, viewer donations, and third- party sponsorships. Given such incentives, some streamers make use of fraudulent means to increase perceived engagement by simulating chatter via fake “chatbots” which can be purchased from shady online marketplaces. This inauthentic engagement can negatively influence recommendation, hurt streamer and viewer trust in the platform, and harm monetization for hon- est streamers. In this paper, we tackle the novel problem of automating detection of chatbots on livestreaming platforms. To this end, we first formalize the livestreaming chatbot detection problem and characterize differences between botted and gen- uine chatter behavior observed from a real-world livestream- ing chatter dataset collected from Twitch.tv. We then propose S HERLOCK , which posits a two-stage approach of detecting chatbotted streams, and subsequently detecting the constituent chatbots. Finally, we demonstrate effectiveness on both real and synthetic data: to this end, we propose a novel strategy for collecting labeled, synthetic chatter dataset (typically unavailable) from such platforms, enabling evaluation of proposed detection approaches against chatbot behaviors with varying signatures. Our approach achieves .97 precision/recall on the real-world dataset, and .80+ F1 scores across most simulated attack settings.

Abstract

Road safety mapping using satellite images is a cost-effective but a challenging problem for smart city planning. The scarcity of labeled data, misalignment and ambiguity makes it hard to learn efficient embeddings in order to classify between safe and dangerous road segments. In this paper, we address the challenges using a region guided attention network. In our model, we extract global features from a base network and augment it with local features obtained using the region guided attention network. In addition, we perform domain adaptation for unlabeled target data. In order to bridge the gap between safe samples and dangerous samples from source and target respectively, we propose a loss function based on within and between class covariance matrices. We conduct experiments on a public dataset of London to show that the algorithm achieves significant results with the classification accuracy of 86.21%. We obtain an increase of 4% accuracy for NYC using domain adaptation network.

Abstract

Narratives of the gig economy are largely perspectives from the global North and the nature of their ride-hailing market. Freelancing or gigging offer contrasting connotations depending on the market and the labour it is situated in. India, with its demographic dividend and employment challenges, view opportunities arising out of the gig- economy differently. To investigate the impact of ride-hailing apps in the Indian market, and the challenges and opportunities it has brought in, we offer learnings from an ethnographic study of Uber drivers in India.

Abstract

The development of building codes for energy efficiency depends on climate zones. National Building Codes of India prescribes five climate zones in India. This classification does not consider fluctuations of outdoor conditions and its effect on indoor comfort conditions. The indoor comfort conditions can be incorporated by using Heating Degree Day (HDD) and Cooling Degree Day (CDD) analysis. Additionally, this classification used mean monthly temperature which cannot capture extreme conditions of the month while the degree day can account for fluctuations in the outdoor temperature and eliminate those periods when heating or cooling systems do not need to operate for a day. This study proposes a new climate zones classification based on hierarchical cluster analysis on 60 Indian locations. The analysis uses climate indices such as HDD, CDD and annual mean relative humidity as variables for clustering analysis. The 60 locations are grouped into 8 climate zones. Three climate zones have only one city as they are distinct from the other location in terms of climate. This updated climate classification may improve the accuracy of the energy conservation codes and building design

Abstract

Air-conditioned buildings are conventionally designed and operated to maintain homogeneous thermal conditions. Maintaining the occupied and unoccupied zones at the same thermal conditions leads to higher energy consumption. More importantly, homogeneous thermal conditions do not address the need for individual thermal comfort preferences. A personal comfort system (PCS) allows the occupants to create desired localized thermal conditions around workstations in the office environment. Using computational fluid dynamic (CFD) and multi-node thermoregulation models, this paper evaluates the feasibility of a PCS with a radiantly cooled partition panel system to achieve thermal comfort. All input parameters for the model were derived from reallife measurements, including thermal characteristics of the room, work desk with radiantly cooled partition, and HVAC systems. A combination of scSTREAM™ and scTETRA™ was used to model the room and the human body (Cradle MSC Software, 2017). The simulation model had a mannequin in a seated position having summer clothing values and office activity metabolic rate. Combinations of three ambient room air temperatures and five panel surface temperatures were investigated to estimate the impact of radiant panels on overall thermal comfort and various body parts of the mannequin. The body parts like the thighs, chest, back, and pelvis showed a low thermal variation in the range of 0.9-1.2°C. The parts such as the head, neck, shoulders, arms, and legs showed a thermal variation in the range of 1.6-2.7°C, while the body parts farthest from the warm torso - the feet, experienced the highest variation in the range of 4.4- 4.5°C. It was observed that the back side of the body was distinctly warmer than the front side of the body throughout the studied cases due to the action of frontplaced radiant panels. It also indicates that at a given room air temperature with an increase in the difference between surface and air temperature, from 0°C to 8°C, all the body

Abstract

This is a short report on the Tutorials and Tech Briefings session of the 12th Innovations in Software Engineering (ISEC 2019) confer- ence held on 14th February 2019 in Pune, India. The tutorials and tech briefings at ISEC have been popular with the participants because they offer a gentle and friendly introduc- tion to cutting edge topics and research at the frontiers of the discipline of software engineering. This year’s track attracted a total of 11 submissions (four tutorial and seven tech briefings). The five submissions that were selected reflect the current interests and directions of the field of software engineering

Abstract

In this paper, a dialogue system for Hospital domain in Telugu, which is a resource-poor Dravidian language, has been built. It handles various hospital and doctor related queries. The main aim of this paper is to present an approach for modelling a dialogue system in a resource-poor language by combining linguistic and domain knowledge. Focusing on the question answering aspect of the dialogue system, we identified Question Classification and Query Processing as the two most important parts of the dialogue system. Our method combines deep learning techniques for question classification and computational rule-based analysis for query processing. Human evaluation of the system has been performed as there is no automated evaluation tool for dialogue systems in Telugu. Our system achieves a high overall rating along with a significantly accurate context-capturing method as shown in the results.

Abstract

The Earth’s climate is not static; it changes according to the natural and anthropogenic climate variability. Anthropogenic forcing due to increase of greenhouse gases in the atmosphere has driven changes in climate variables globally. Changes in climatological variables have severe impact on global hydrological cycle affecting the severity and occurrence of natural hazards such as floods and droughts. Estimation of projections under climate signals with statistical and dynamic downscaling models and integration with water resource management models for the impact assessment have gained much attention. The fine-resolution climate change predictions of dynamic regional climate model (RCM) outputs, which include regional parameterization, have been widely applied in the hydrological impact assessment studies. Advancement of the Coordinated Regional Downscaling Experiment (CORDEX) program has enabled the use of RCMs in regional impact assessment which has progressed in recent years. CORDEX model outputs were considered to be valuable in terms of establishing large ensembles of climate projections based on regional climate downscaling all over the world. However, the simulations of RCM outputs have to be evaluated to check the reliability in reproducing the observed climate variability over a region. The present study demonstrates the use of bias-corrected CORDEX model simulation in analyzing the regional-scale climatology at river basin scale, Krishna river basin (KRB), India. The precipitation and temperature simulations from CORDEX models with RCP 4.5 were evaluated for the historical data for the period of 1965 to 2014 with India Meteorological Department (IMD) gridded rainfall and temperature data sets cropped over the basin. The projected increase

Abstract

Conservation efforts to protect biodiversity rely on an accurate identification process. In the case of plant identification, traditional methods used are manual, time-consuming and require a degree of expertise to operate. As a result, there is an increasing interest today for an automated plant identification system. Such a system can help in aiding plant-related education, promoting ecotourism, creating a digital heritage for plant species among many others. We propose a solution using modern convolutional neural network architectures which achieves stateof-the-art performance for plant classification in the wild. An exhaustive set of experiments are performed to classify 112 species of plants from the challenging Indic-Leaf dataset. The best performing model gives Top-1 precision of 90.08 and Top-5 precision of 96.90.