Abstract

This paper describes our system (Fermi) for Task 4: Hyper-partisan News detection of SemEval-2019. We use simple text classification algorithms by transforming the input features to a reduced feature set. We aim to find the right number of features useful for efficient classification and explore multiple training models to evaluate the performance of these text classification algorithms. Our team - Fermi’s model achieved an accuracy of 59.10% and an F1 score of 69.5% on the official test data set. In this paper, we provide a detailed description of the approach as well as the results obtained in the task.

Abstract

We present a data set of 1460 Hindi-English code-mixed tweets consisting of 20,949 tokens labelled with Proposition Bank labels marking their semantic roles. We created verb frames for complex predicates present in the corpus and formulated mappings from Paninian dependency labels to Proposition Bank labels. With the help of these mappings and the dependency tree, we propose a baseline rule based system for Semantic Role Labelling of Hindi-English code-mixed data. We obtain an accuracy of 96.74% for Argument Identification and are able to further classify 73.93% of the labels correctly. While there is relevant ongoing research on Semantic Role Labelling (SRL) and on building tools for code-mixed social media data, this is the first attempt at labelling semantic roles in Hindi-English codemixed data, to the best of our knowledge.

Abstract

We present a system for automating Semantic Role Labelling of Hindi-English code-mixed tweets. We explore the issues posed by noisy, user generated code-mixed social media data. We also compare the individual effect of various linguistic features used in our system. Our proposed model is a 2-step system for automated labelling which gives an overall accuracy of 84% for Argument Classification, marking a 10% increase over the existing rulebased baseline model. This is the first attempt at building a statistical Semantic Role Labeller for Hindi-English code-mixed data, to the best of our knowledge

Abstract

Cuff-less blood pressure (BP) is essential for continuous health monitoring to prevent diseases such as hypertension. Due to the discomfort caused by inflation and deflation of the cuff, it is not possible to monitor continuously. Although pulse transit time (PTT) based approach is commonly used, other parameters also vary with BP. Multi-parameter models are developed using regression analysis, to estimate systolic blood pressure (SBP) and diastolic blood pressure (DBP). Hence, the correlation of multiple extracted features with the blood pressure is proved. To achieve this, simultaneous electrocardiogram (ECG) and photoplethysmographic (PPG) along with respective BP data were collected. The developed algorithm uses wavelet transformation on ECG and PPG signals for detection of the occurrence of essential wave points precisely, even in the presence of artifacts. Pulse wave analysis (PWA) is performed to create a feature vector. From the experimental results, it is found that, the SBP model gives mean error of 0.4916 mmHg, with standard deviation of 6.3986 mmHg, whereas for DBP model, mean error is 0.2527 mmHg and standard deviation is 3.2835 mmHg which is acceptable as per the British Hypertension Society (BHS) and Association for the Advancement of Medical Instruments (AAMI) standards. After the removal of BP oddities, mean absolute error improves from 5.625 to 3.854 mmHg for SBP and from 2.564 to 2.144 mmHg for DBP.

Abstract

Directed Energy System (DES) is highly efficient to damage both static and dynamic targets. Each target demands a minimum lethal fluence to make engagement successful, depending on the material, thickness, coating and structural properties. DES provides the required lethal fluence on the target to reach the melting or burning temperature. The static target consumes approximately constant fluence, but for the dynamic target, the flux density requirement estimation varies within the dwell time, which is proportional to the distance between the DES and the target. In this paper, the initial power requirement of DES has been estimated based on target specification.

Abstract

Social dynamics are based on human needs for trust, support, resource sharing, irrespective of whether they operate in real life or in a virtual setting. Massively multiplayer online role-playing games (MMORPGS) serve as enablers of leisurely social activity and are important tools for social interactions. Past research has shown that socially dense gaming environments like MMORPGs can be used to study important social phenomena, which may operate in real life, too. We describe the process of social exploration to entail the following components 1) finding the balance between personal and social time 2) making choice between a large number of weak ties or few strong social ties. 3) finding a social group. In general, these are the major determinants of an individual’s social life. This paper looks into the phenomenon of social exploration in an activity based online social environment. We study this process through the lens of the following research questions, 1) What are the different social behavior types? 2) Is there a change in a player’s social behavior over time? 3) Are certain social behaviors more stable than the others? 4) Can longitudinal research of player behavior help shed light on the social dynamics and processes in the network? We use an unsupervised machine learning approach to come up with 4 different social behavior types - Lone Wolf, Pack Wolf of Small Pack, Pack Wolf of a Large Pack and Social Butterfly. The types represent the degree of socialization of players in the game. Our research reveals that social behaviors change with time. While lone wolf and pack wolf of small pack are more stable social behaviors, pack wolf of large pack and social butterflies are more transient. We also observe that players progressively move from large groups with weak social ties to settle in small groups with stronger ties. Index Terms—Social Exploration, Social Behavior Typology, MMORPG, Clusterin

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

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