Abstract

We describe our participation in all the subtasks of the Germeval 2021 shared task on the identification of Toxic, Engaging, and FactClaiming Comments. Our system is an ensemble of state-of-the-art pre-trained models finetuned with carefully engineered features. We show that feature engineering and data augmentation can be helpful when the training data is sparse. We achieve an F1 score of 66.87, 68.93, and 73.91 in Toxic, Engaging, and Fact-Claiming comment identification subtasks.

Abstract

Earthquake safety of buildings is one of the primary concerns of structural engineers throughout the world. The performance of buildings during past earthquakes has brought out the lacunas in design, analysis and execution of these structures. The constant endeavour for uniqueness has led to the distribution of irregularities along the plan and height of buildings. One of such attempts is the development of Open Ground Storey (OGS) buildings. It is the dominant parameter having vertical irregularity, if not rectified, may often lead to the collapse of structure. Reinforced concrete building with OGS; absence of infill wall in a ground storey, is prevailing construction practice in most places in India. It causes a sudden decrease in lateral stiffness (K) and strength (V), from adjacent upper to ground storey, results in accumulation of stresses due to large lateral displacement in ground storey columns to cause soft storey effect. The problem can be solved by increasing K and V of the ground storey relative to the adjacent upper storey. Seismic codes specify the design process for buildings with OGS by relative K and V of ground and adjacent upper storey. Quantifying design criteria for such structural configurations based on Design Amplification Factor (DAF) for ground storey columns is preferable. K and V of storey depends on masonry strength, central opening (OP) in infills and interaction between wall infill and frame. In the current study, DAF is proposed to overcome OGS effect considering the above parameters. Additional parameters like Stiffness factor (KF) and strength factor (VF), ratios of elastic lateral stiffness (KE) and maximum

Abstract

The advent of the cracked moment of inertia (MoI) in Indian code provisions has sparked many discussions and confusions regarding what MoI is to be used in the design of structures in service load case and ultimate load case. The intent of this study is to understand the uncracked and cracked moment of inertia, what code provisions recommend, their applicability and the possible reasoning behind the recommendations. Solved examples are presented along with this review study to clear the usage of cracked MoI and u n d e r s t a n d t h e s i g n i  c a n c e o f s u c h recommendations.

Abstract

An effective earthquake (Mw 7.9) struck Alaska on 3 November 2002. This earthquake ruptured 340 km along Susitna Glacier, Denali, and Totschunda faults in Central Alaska. The peak ground acceleration (PGA) was recorded about 0.32 g at station PS10, which was located 3 km from the fault rupture. The PGA would have recorded a high value if more instruments had been installed in the region. A numerical study has been conducted to find out the possible ground motion record that could occur at maximum horizontal slip during the Denali earthquake. The current study overcomes the limitation of number of elementsto model the Denali fault. These numerical results are compared with observed ground motions. It is observed that the ground motions obtained through numerical analysis are in good agreement with observed ground motions. From numerical results, it is observed that the possible expected PGA is 0.62 g at maximum horizontal slip of Denali fault.

Abstract

Hazard plays a vital role in assessing the risk of any area. For earthquake hazard estimation, it is essential to obtain ground motion records from various seismic stations. However, it is not always easy to get ground motion data. The present study is an attempt to generate ground motions of the recent September 24, 2013, Pakistan earthquake using modified semi-empirical approach, which is based on w2 model. The first part of the method considers a time series having the basic spectral shape of acceleration. The deterministic model of rupture source has been used in the second part ofthe method to simulate the envelope of accelerogram. For the study, a MATLABcode is written to generate synthetic accelerograms atstations Awaran, Panjgur, Tagas, Korak, and Gajar. The results are compared with Ground Motion Prediction Equation (GMPE) proposed byRamkrishnan et al., in 2019 [1]. The PGAvalues obtained from modified semi-empirical method gives satisfactorily good results in comparison with the PGAvaluesfromGMPE. However, slight variation is observed between synthetic accelerogram PGAvalues and GMPE values at Gajar, Korak, Tagas, Panjgur stations.

Abstract

Social media plays a crucial role in today’s society. It results in paradigm changes in how people relate and communicate, convey and exchange ideas. Moreover, social media has evolved into critical knowledge networks for consumers and also affects decision-making. In elections, social media became an integral part of political campaigning to reach a greater audience and gather more support. The 2019 Lok Sabha election saw a massive spike in the usage of online social media platforms such as Twitter, Facebook, and WhatsApp; with every major political party launching its own organized social media campaigns by investing vast amounts of money. Without limiting mainstream media, almost all Indian political leaders started using social media, especially Facebook and Twitter, to express themselves. In 2014, Bhartiya Janta Party (BJP) took one step ahead in organizing the campaign by launching its app - NaMo App. We focus our research on Twitter and NaMo App during the 2019 Lok Sabha elections and Citizenship Amendment Act (CAA) protests. Twitter is one such platform where every individual can express their views and is not biased. In contrast, NaMo App is one of the first apps centered around a specific political party. It acted as a digital medium for Bhartiya Janta Party (BJP) for organizing the political campaign to make people’s opinion in their favor. This research aims to characterize the role of the NaMo App in a more traditional network as Twitter in shaping political discourse and studies the existence of an online echo chamber on Twitter. We began by analyzing the amount and type of content shared using the NaMo App on Twitter. We performed content and network analysis for the existence of the echo chamber. We also applied the Hawkes process to see the influence that NaMo App has on Twitter. Through this research, we can conclude that the users who share content using NaMo App, may be part of an online echo chamber and are likely to be BJP workers. We show the reach and influence that the NaMo App has on Twitter is significantly less, indicating its inability to break through the diverse audience and change the narrative on Twitter.

Abstract

Online recruitment platforms have abundant user-generated content in the form of job postings, candidate, and company profiles. This content when ingested into Knowledge bases causes redundant, ambiguous, and noisy entities. These multiple (non-standardized) representation of the entities deteriorates the performance of downstream tasks such as job recommender systems, search systems, and question answering. Therefore, making it imperative to canonicalize the entities to improve the performance of such tasks. Recent research discusses either statistical similarity measures or deep learning methods like word-embedding or siamese network-based representations for canonicalization. In this paper, we propose a Kernel-based Canonicalization Network (KCNet) that outperforms all the known statistical and deep learning methods. We also show that the use of side information such as industry type, url of websites, etc. further enhances the performance of the proposed method. Our experiments on 351,600 entities (companies, institutes, skills, and designations) from a popular online recruitment platform demonstrate that the proposed method improves the overall F1-score by 23% compared to the previous baselines, which results in coherent clusters of unique entities.

Abstract

Social media platforms play an important role in democratic processes. During the 2019 General Elections of India, political parties and politicians widely used Twitter to share their ideals, advocate their agenda and gain popularity. Twitter served as a ground for journalists, politicians and voters to interact. The organic nature of these interactions can be upended by malicious accounts on Twitter, which end up being suspended or deleted from the platform. Such accounts aim to modify the reach of content by inorganically interacting with particular handles. These interactions are a threat to the integrity of the platform, as such activity has the potential to affect entire results of democratic processes. In this work, we design a feature extraction framework which compactly captures potentially insidious interaction patterns. Our proposed features are designed to bring out communities amongst the users that work to boost the content of particular accounts. We use Hyperbolic Hierarchical Clustering (HypHC) which represents the features in the hyperbolic manifold to further separate such communities. HypHC gives the added benefit of representing these features in a lower dimensional space -- thus serving as a dimensionality reduction technique. We use these features to distinguish between different classes of users that emerged in the aftermath of the 2019 General Elections of India. Amongst the users active on Twitter during the elections, 2.8% of the users participating were suspended and 1% of the users were deleted from the platform. We demonstrate the effectiveness of our proposed features in differentiating between regular users (users who …

Abstract

The past decade has witnessed a rapid increase in technology ownership across rural areas of India, signifying the potential for ICT initiatives to empower rural households. In our work, we focus on the web infrastructure of one such ICT - Digital Green that started in 2008. Following a participatory approach for content production, Digital Green disseminates instructional agricultural videos to smallholder farmers via human mediators to improve the adoption of farming practices. Their web-based data tracker, CoCo, captures data related to these processes, storing the attendance and adoption logs of over 2.3 million farmers across three continents and twelve countries. Using this data, we model the components of the Digital Green ecosystem involving the past attendance-adoption behaviours of farmers, the content of the videos screened to them and their demographic features across five states in India. We use statistical tests to identify different factors which distinguish farmers with higher adoption rates to understand why they adopt more than others. Our research finds that farmers with higher adoption rates adopt videos of shorter duration and belong to smaller villages. The co-attendance and co-adoption networks of farmers indicate that they greatly benefit from past adopters of a video from their village and group when it comes to adopting practices from the same video. Following our analysis, we model the adoption of practices from a video as a prediction problem to identify and assist farmers who might face challenges in adoption in each of the five states. We experiment with different model architectures and achieve macro-f1 scores

Abstract

Social media has grown exponentially in a short period, coming to the forefront of communications and online interactions. Despite their rapid growth, social media platforms have been unable to scale to different languages globally and remain inaccessible to many. In this paper, we characterize Koo, a multilingual micro-blogging site that rose in popularity in 2021, as an Indian alternative to Twitter. We collected a dataset of 4.07 million users, 163.12 million follower-following relationships, and their content and activity across 12 languages. We study the user demographic along the lines of language, location, gender, and profession. The prominent presence of Indian languages in the discourse on Koo indicates the platform's success in promoting regional languages. We observe Koo's follower-following network to be much denser than Twitter's, comprising of closely-knit linguistic communities. An N-gram analysis …