arXiv subjects

Rabindra Lamsal

Publications and source records attributed to Rabindra Lamsal.

16 recordsLinked to original sources

arXiv2026

CityLLM: A framework for natural-language querying of semantic 3D city models

Semantic 3D city models provide rich geometric and semantic information, but remain challenging for non-experts and interdisciplinary researchers to access and query due to their complex structures and specialized data formats. To address this issue, we present CityLLM, a framework for natural-language querying of semantic 3D city models alongside complementary urban datasets. The framework combines spatial and graph databases within an LLM-based workflow that supports iterative query refinement and cross-database chaining. We evaluate CityLLM on a CityJSON dataset of Rotterdam (853 LoD2 buildings) using GPT-OSS, Gemini 3.1, and GPT-5.4, along with selected variants, across multiple metrics: answer correctness, visualization correctness, query success, and retry attempts. A total of 54 natural-language queries are curated across four scenarios: spatial, graph, cross-database, and conversational. Results show strong overall performance, with answer correctness ranging from 85.2% to 100%, visualization correctness from 92.9% to 100%, a 100% query success rate, and fewer than three retries across all 54 queries. Overall, the findings suggest that CityLLM provides a lightweight and extensible approach for conversational access to semantic 3D city data.

cs.CL↗

arXiv2026

IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations

The Industry Foundation Classes (IFC) standard is central to building data exchange across the lifecycle, from design and construction to facility management and Digital Twin integration. In operational settings, stakeholders increasingly require access to building information without specialist knowledge of IFC's complex, deeply nested schema, motivating natural language interfaces. Existing LLM-based querying approaches typically rely on a single data representation, which is not equally suited to attribute retrieval and spatial reasoning. We present IfcLLM, a framework that combines complementary relational and graph representations, routing each query type to the more suitable backend. An LLM agent integrates both through iterative retry-and-refine reasoning, recovering from failures without user input. Evaluated across three IFC models on 30 query scenarios, our implementation achieves first-attempt accuracy between 93.3% and 100%, with all failed queries resolved via a fallback LLM. Built on an open-weight LLM, it supports local deployment in data-sensitive AEC settings.

cs.CL↗

arXiv2025

Langformers: Unified NLP Pipelines for Language Models

Transformer-based language models have revolutionized the field of natural language processing (NLP). However, using these models often involves navigating multiple frameworks and tools, as well as writing repetitive boilerplate code. This complexity can discourage non-programmers and beginners, and even slow down prototyping for experienced developers. To address these challenges, we introduce Langformers, an open-source Python library designed to streamline NLP pipelines through a unified, factory-based interface for large language model (LLM) and masked language model (MLM) tasks. Langformers integrates conversational AI, MLM pretraining, text classification, sentence embedding/reranking, data labelling, semantic search, and knowledge distillation into a cohesive API, supporting popular platforms such as Hugging Face and Ollama. Key innovations include: (1) task-specific factories that abstract training, inference, and deployment complexities; (2) built-in memory and streaming for conversational agents; and (3) lightweight, modular design that prioritizes ease of use. Documentation: https://langformers.com

cs.CL↗

arXiv2025

"Actionable Help" in Crises: A Novel Dataset and Resource-Efficient Models for Identifying Request and Offer Social Media Posts

During crises, social media serves as a crucial coordination tool, but the vast influx of posts--from "actionable" requests and offers to generic content like emotional support, behavioural guidance, or outdated information--complicates effective classification. Although generative LLMs (Large Language Models) can address this issue with few-shot classification, their high computational demands limit real-time crisis response. While fine-tuning encoder-only models (e.g., BERT) is a popular choice, these models still exhibit higher inference times in resource-constrained environments. Moreover, although distilled variants (e.g., DistilBERT) exist, they are not tailored for the crisis domain. To address these challenges, we make two key contributions. First, we present CrisisHelpOffer, a novel dataset of 101k tweets collaboratively labelled by generative LLMs and validated by humans, specifically designed to distinguish actionable content from noise. Second, we introduce the first crisis-specific mini models optimized for deployment in resource-constrained settings. Across 13 crisis classification tasks, our mini models surpass BERT (also outperform or match the performance of RoBERTa, MPNet, and BERTweet), offering higher accuracy with significantly smaller sizes and faster speeds. The Medium model is 47% smaller with 3.8% higher accuracy at 3.5x speed, the Small model is 68% smaller with a 1.8% accuracy gain at 7.7x speed, and the Tiny model, 83% smaller, matches BERT's accuracy at 18.6x speed. All models outperform existing distilled variants, setting new benchmarks. Finally, as a case study, we analyze social media posts from a global crisis to explore help-seeking and assistance-offering behaviours in selected developing and developed countries.

cs.CL↗

arXiv2024

CReMa: Crisis Response through Computational Identification and Matching of Cross-Lingual Requests and Offers Shared on Social Media

During times of crisis, social media platforms play a crucial role in facilitating communication and coordinating resources. In the midst of chaos and uncertainty, communities often rely on these platforms to share urgent pleas for help, extend support, and organize relief efforts. However, the overwhelming volume of conversations during such periods can escalate to unprecedented levels, necessitating the automated identification and matching of requests and offers to streamline relief operations. Additionally, there is a notable absence of studies conducted in multi-lingual settings, despite the fact that any geographical area can have a diverse linguistic population. Therefore, we propose CReMa (Crisis Response Matcher), a systematic approach that integrates textual, temporal, and spatial features to address the challenges of effectively identifying and matching requests and offers on social media platforms during emergencies. Our approach utilizes a crisis-specific pre-trained model and a multi-lingual embedding space. We emulate human decision-making to compute temporal and spatial features and non-linearly weigh the textual features. The results from our experiments are promising, outperforming strong baselines. Additionally, we introduce a novel multi-lingual dataset simulating help-seeking and offering assistance on social media in 16 languages and conduct comprehensive cross-lingual experiments. Furthermore, we analyze a million-scale geotagged global dataset to understand patterns in seeking help and offering assistance on social media. Overall, these contributions advance the field of crisis informatics and provide benchmarks for future research in the area.

cs.CL↗

arXiv2024

CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts

Social media platforms play an essential role in crisis communication, but analyzing crisis-related social media texts is challenging due to their informal nature. Transformer-based pre-trained models like BERT and RoBERTa have shown success in various NLP tasks, but they are not tailored for crisis-related texts. Furthermore, general-purpose sentence encoders are used to generate sentence embeddings, regardless of the textual complexities in crisis-related texts. Advances in applications like text classification, semantic search, and clustering contribute to the effective processing of crisis-related texts, which is essential for emergency responders to gain a comprehensive view of a crisis event, whether historical or real-time. To address these gaps in crisis informatics literature, this study introduces CrisisTransformers, an ensemble of pre-trained language models and sentence encoders trained on an extensive corpus of over 15 billion word tokens from tweets associated with more than 30 crisis events, including disease outbreaks, natural disasters, conflicts, and other critical incidents. We evaluate existing models and CrisisTransformers on 18 crisis-specific public datasets. Our pre-trained models outperform strong baselines across all datasets in classification tasks, and our best-performing sentence encoder improves the state-of-the-art by 17.43% in sentence encoding tasks. Additionally, we investigate the impact of model initialization on convergence and evaluate the significance of domain-specific models in generating semantically meaningful sentence embeddings. The models are publicly available at: https://huggingface.co/crisistransformers

cs.CL↗

arXiv2024

Semantically Enriched Cross-Lingual Sentence Embeddings for Crisis-related Social Media Texts

Tasks such as semantic search and clustering on crisis-related social media texts enhance our comprehension of crisis discourse, aiding decision-making and targeted interventions. Pre-trained language models have advanced performance in crisis informatics, but their contextual embeddings lack semantic meaningfulness. Although the CrisisTransformers family includes a sentence encoder to address the semanticity issue, it remains monolingual, processing only English texts. Furthermore, employing separate models for different languages leads to embeddings in distinct vector spaces, introducing challenges when comparing semantic similarities between multi-lingual texts. Therefore, we propose multi-lingual sentence encoders (CT-XLMR-SE and CT-mBERT-SE) that embed crisis-related social media texts for over 50 languages, such that texts with similar meanings are in close proximity within the same vector space, irrespective of language diversity. Results in sentence encoding and sentence matching tasks are promising, suggesting these models could serve as robust baselines when embedding multi-lingual crisis-related social media texts. The models are publicly available at: https://huggingface.co/crisistransformers.

cs.CL↗

arXiv2024

From Pro, Anti to Informative and Hesitant: An Infoveillance study of COVID-19 vaccines and vaccination discourse on Twitter

COVID-19 pandemic has brought unprecedented challenges to the world, and vaccination has been a key strategy to combat the disease. Since Twitter is one of the most widely used public microblogging platforms, researchers have analysed COVID-19 vaccines and vaccination Twitter discourse to explore the conversational dynamics around the topic. While contributing to the crisis informatics literature, we curate a large-scale geotagged Twitter dataset, GeoCovaxTweets Extended, and explore the discourse through multiple spatiotemporal analyses. This dataset covers a longer time span of 38 months, from the announcement of the first vaccine to the availability of booster doses. Results show that 43.4% of the collected tweets, although containing phrases and keywords related to vaccines and vaccinations, were unrelated to the COVID-19 context. In total, 23.1% of the discussions on vaccines and vaccinations were classified as Pro, 16% as Hesitant, 11.4% as Anti, and 6.1% as Informative. The trend shifted towards Pro and Informative tweets globally as vaccination programs progressed, indicating a change in the public's perception of COVID-19 vaccines and vaccination. Furthermore, we explored the discourse based on account attributes, i.e., followers counts and tweet counts. Results show a significant pattern of discourse differences. Our findings highlight the potential of harnessing a large-scale geotagged Twitter dataset to understand global public health communication and to inform targeted interventions aimed at addressing vaccine hesitancy.

cs.SI↗

arXiv2023

BillionCOV: An Enriched Billion-scale Collection of COVID-19 tweets for Efficient Hydration

The COVID-19 pandemic introduced new norms such as social distancing, face masks, quarantine, lockdowns, travel restrictions, work/study from home, and business closures, to name a few. The pandemic's seriousness made people vocal on social media, especially on microblogs such as Twitter. Researchers have been collecting and sharing large-scale datasets of COVID-19 tweets since the early days of the outbreak. Sharing raw Twitter data with third parties is restricted; users need to hydrate tweet identifiers in a public dataset to re-create the dataset locally. Large-scale datasets that include original tweets, retweets, quotes, and replies have tweets in billions which takes months to hydrate. The existing datasets carry issues related to proportion and redundancy. We report that more than 500 million tweet identifiers point to deleted or protected tweets. In order to address these issues, this paper introduces an enriched global billion-scale English-language COVID-19 tweets dataset, BillionCOV, that contains 1.4 billion tweets originating from 240 countries and territories between October 2019 and April 2022. Importantly, BillionCOV facilitates researchers to filter tweet identifiers for efficient hydration. This paper discusses associated methods to fetch raw Twitter data for a set of tweet identifiers, presents multiple tweets' distributions to provide an overview of BillionCOV, and finally, reviews the dataset's potential use cases.

cs.SI↗

arXiv2023

A Twitter narrative of the COVID-19 pandemic in Australia

Social media platforms contain abundant data that can provide comprehensive knowledge of historical and real-time events. During crisis events, the use of social media peaks, as people discuss what they have seen, heard, or felt. Previous studies confirm the usefulness of such socially generated discussions for the public, first responders, and decision-makers to gain a better understanding of events as they unfold at the ground level. This study performs an extensive analysis of COVID-19-related Twitter discussions generated in Australia between January 2020, and October 2022. We explore the Australian Twitterverse by employing state-of-the-art approaches from both supervised and unsupervised domains to perform network analysis, topic modeling, sentiment analysis, and causality analysis. As the presented results provide a comprehensive understanding of the Australian Twitterverse during the COVID-19 pandemic, this study aims to explore the discussion dynamics to aid the development of future automated information systems for epidemic/pandemic management.

cs.SI↗

arXiv2023

GeoCovaxTweets: COVID-19 Vaccines and Vaccination-specific Global Geotagged Twitter Conversations

Social media platforms provide actionable information during crises and pandemic outbreaks. The COVID-19 pandemic has imposed a chronic public health crisis worldwide, with experts considering vaccines as the ultimate prevention to achieve herd immunity against the virus. A proportion of people may turn to social media platforms to oppose vaccines and vaccination, hindering government efforts to eradicate the virus. This paper presents the COVID-19 vaccines and vaccination-specific global geotagged tweets dataset, GeoCovaxTweets, that contains more than 1.8 million tweets, with location information and longer temporal coverage, originating from 233 countries and territories between January 2020 and November 2022. The paper discusses the dataset's curation method and how it can be re-created locally, and later explores the dataset through multiple tweets distributions and briefly discusses its potential use cases. We anticipate that the dataset will assist the researchers in the crisis computing domain to explore the conversational dynamics of COVID-19 vaccines and vaccination Twitter discourse through numerous spatial and temporal dimensions concerning trends, shifts in opinions, misinformation, and anti-vaccination campaigns.

cs.SI↗

arXiv2022

Where did you tweet from? Inferring the origin locations of tweets based on contextual information

Public conversations on Twitter comprise many pertinent topics including disasters, protests, politics, propaganda, sports, climate change, epidemics/pandemic outbreaks, etc., that can have both regional and global aspects. Spatial discourse analysis rely on geographical data. However, today less than 1% of tweets are geotagged; in both cases--point location or bounding place information. A major issue with tweets is that Twitter users can be at location A and exchange conversations specific to location B, which we call the Location A/B problem. The problem is considered solved if location entities can be classified as either origin locations (Location As) or non-origin locations (Location Bs). In this work, we propose a simple yet effective framework--the True Origin Model--to address the problem that uses machine-level natural language understanding to identify tweets that conceivably contain their origin location information. The model achieves promising accuracy at country (80%), state (67%), city (58%), county (56%) and district (64%) levels with support from a Location Extraction Model as basic as the CoNLL-2003-based RoBERTa. We employ a tweet contexualizer (locBERT) which is one of the core components of the proposed model, to investigate multiple tweets' distributions for understanding Twitter users' tweeting behavior in terms of mentioning origin and non-origin locations. We also highlight a major concern with the currently regarded gold standard test set (ground truth) methodology, introduce a new data set, and identify further research avenues for advancing the area.

cs.CL↗

arXiv2022

Twitter conversations predict the daily confirmed COVID-19 cases

As of writing this paper, COVID-19 (Coronavirus disease 2019) has spread to more than 220 countries and territories. Following the outbreak, the pandemic's seriousness has made people more active on social media, especially on the microblogging platforms such as Twitter and Weibo. The pandemic-specific discourse has remained on-trend on these platforms for months now. Previous studies have confirmed the contributions of such socially generated conversations towards situational awareness of crisis events. The early forecasts of cases are essential to authorities to estimate the requirements of resources needed to cope with the outgrowths of the virus. Therefore, this study attempts to incorporate the public discourse in the design of forecasting models particularly targeted for the steep-hill region of an ongoing wave. We propose a sentiment-involved topic-based latent variables search methodology for designing forecasting models from publicly available Twitter conversations. As a use case, we implement the proposed methodology on Australian COVID-19 daily cases and Twitter conversations generated within the country. Experimental results: (i) show the presence of latent social media variables that Granger-cause the daily COVID-19 confirmed cases, and (ii) confirm that those variables offer additional prediction capability to forecasting models. Further, the results show that the inclusion of social media variables introduces 48.83--51.38% improvements on RMSE over the baseline models. We also release the large-scale COVID-19 specific geotagged global tweets dataset, MegaGeoCOV, to the public anticipating that the geotagged data of this scale would aid in understanding the conversational dynamics of the pandemic through other spatial and temporal contexts.

cs.CL↗

arXiv2022

Socially Enhanced Situation Awareness from Microblogs using Artificial Intelligence: A Survey

The rise of social media platforms provides an unbounded, infinitely rich source of aggregate knowledge of the world around us, both historic and real-time, from a human perspective. The greatest challenge we face is how to process and understand this raw and unstructured data, go beyond individual observations and see the "big picture"--the domain of Situation Awareness. We provide an extensive survey of Artificial Intelligence research, focusing on microblog social media data with applications to Situation Awareness, that gives the seminal work and state-of-the-art approaches across six thematic areas: Crime, Disasters, Finance, Physical Environment, Politics, and Health and Population. We provide a novel, unified methodological perspective, identify key results and challenges, and present ongoing research directions.

cs.LG↗

arXiv2020

Predicting Outcome of Indian Premier League (IPL) Matches Using Machine Learning

Cricket, especially the Twenty20 format, has maximum uncertainty, where a single over can completely change the momentum of the game. With millions of people following the Indian Premier League (IPL), developing a model for predicting the outcome of its matches is a real-world problem. A cricket match depends upon various factors, and in this work, the factors which significantly influence the outcome of a Twenty20 cricket match are identified. Each player's performance in the field is considered to find out the overall weight (relative strength) of the teams. A multivariate regression based solution is proposed to calculate points for each player in the league and the overall weight of a team is computed based on the past performance of the players who have appeared most for the team. Finally, a dataset is modeled based on the identified seven factors which influence the outcome of an IPL match. Six machine learning models were trained and used for predicting the outcome of each 2018 IPL match, 15 minutes before the gameplay, immediately after the toss. Three of the trained models were seen to be correctly predicting more than 40 matches, with Multilayer Perceptron outperforming all other models with an impressive accuracy of 71.66%.

stat.AP↗

arXiv2019

Determining Optimal Number of k-Clusters based on Predefined Level-of-Similarity

This paper proposes a centroid-based clustering algorithm which is capable of clustering data-points with n-features, without having to specify the number of clusters to be formed. The core logic behind the algorithm is a similarity measure, which collectively decides whether to assign an incoming data-point to a pre-existing cluster, or create a new cluster and assign the data-point to it. The proposed clustering algorithm is application-specific and is applicable when the need is to perform clustering analysis of a stream of data-points, where the similarity measure between an incoming data-point and the cluster to which the data-point is to be associated with, is greater than the predefined Level-of-Similarity.

cs.LG↗