Related papers: Non-Parametric Temporal Adaptation for Social Medi…
Performance of neural models for named entity recognition degrades over time, becoming stale. This degradation is due to temporal drift, the change in our target variables' statistical properties over time. This issue is especially…
Language use changes over time, and this impacts the effectiveness of NLP systems. This phenomenon is even more prevalent in social media data during crisis events where meaning and frequency of word usage may change over the course of…
In machine learning, temporal shifts occur when there are differences between training and test splits in terms of time. For streaming data such as news or social media, models are commonly trained on a fixed corpus from a certain period of…
Extracting topics from large collections of unstructured text-documents has become a central task in current NLP applications and algorithms like NMF, LDA as well as their generalizations are the well-established current state of the art.…
With the proliferation of social media, many studies resort to social media to construct datasets for developing social meaning understanding systems. For the popular case of Twitter, most researchers distribute tweet IDs without the actual…
In this thesis, we propose an approach to identity resolution across social media platforms using the topics, sentiments, and timings of the posts on the platforms. After collecting the public posts of around 5000 profiles from Disqus and…
This article presents a novel approach for learning low-dimensional distributed representations of users in online social networks. Existing methods rely on the network structure formed by the social relationships among users to extract…
Social media data exhibits severe redundancy caused by its noisy nature. It leads to increased training time and model bias in its processing. To address this issue, we propose a novel Generative Deduplication framework for social media…
Online social media platforms are turning into the prime source of news and narratives about worldwide events. However,a systematic summarization-based narrative extraction that can facilitate communicating the main underlying events is…
Hashtags have become a powerful tool in social platforms such as Twitter to categorize and search for content, and to spread short messages across members of the social network. In this paper, we study temporal hashtag usage practices in…
Text data is inherently temporal. The meaning of words and phrases changes over time, and the context in which they are used is constantly evolving. This is not just true for social media data, where the language used is rapidly influenced…
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…
Twitter serves as a data source for many Natural Language Processing (NLP) tasks. It can be challenging to identify topics on Twitter due to continuous updating data stream. In this paper, we present an unsupervised graph based framework to…
Large pre-trained language models (LPLM) have shown spectacular success when fine-tuned on downstream supervised tasks. Yet, it is known that their performance can drastically drop when there is a distribution shift between the data used…
Social media such as Twitter provide valuable information to crisis managers and affected people during natural disasters. Machine learning can help structure and extract information from the large volume of messages shared during a crisis;…
A major challenge in paraphrase research is the lack of parallel corpora. In this paper, we present a new method to collect large-scale sentential paraphrases from Twitter by linking tweets through shared URLs. The main advantage of our…
Language features are evolving in real-world social media, resulting in the deteriorating performance of text classification in dynamics. To address this challenge, we study temporal adaptation, where models trained on past data are tested…
Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual…
Twitter data is extremely noisy -- each tweet is short, unstructured and with informal language, a challenge for current topic modeling. On the other hand, tweets are accompanied by extra information such as authorship, hashtags and the…
Given the rapidly evolving nature of social media and people's views, word usage changes over time. Consequently, the performance of a classifier trained on old textual data can drop dramatically when tested on newer data. While research in…