On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “micro-blogging”

A novel sentence embedding based topic detection method for micro-blogcs.IR

Paper presents a novel neural network method for topic detection in micro-blogs.

problem Challenging topic detection without known topic count.

method Unsupervised neural sentence embedding model with attention mechanism.

result Improved clustering algorithm (RADBSCAN) discovers topics based on dataset character.

topic detection neural networks micro-blogs unsupervised learning embedding

2020-06-10abs ↗pdf ↗

Detection of financial opportunities in micro-blogging data with a stacked classification systemq-fin.ST

System detects financial opportunities in tweets with high precision.

problem Detecting valuable financial insights in micro-blogging data.

method Stacked Machine Learning classification system with NLP features.

result System achieves precision up to 83% in detecting financial opportunities.

financial opportunities micro-blogging stacked classification NLP machine learning

2024-03-29abs ↗pdf ↗

Visualizing the Financial Impact of Presidential Tweets on Stock Marketsq-fin.ST

Analyzes how Trump's tweets impact global stock markets.

problem Understanding the financial impact of presidential tweets on stock markets.

method Examined tweets from Donald Trump's presidency, collected from The Guardian and Bloomberg, and analyzed their effect on equity indices.

result Identified tweets that significantly influenced stock market indices.

presidential tweets stock market financial impact Donald Trump equity indices

2021-01-08abs ↗pdf ↗

Investigating Classification Techniques with Feature Selection For Intention Mining From Twitter Feedcs.IR

This paper examines feature selection for extracting user intentions from Twitter.

problem Extracting user intentions from informal, misspelled tweets.

method Developed a dataset from Twitter feeds, used two feature selection techniques (Information Gain and hybrid forward selection), and applied four classification algorithms.

result The hybrid feature selection approach outperformed the Information Gain method.

Twitter Feature Selection Intention Mining Text Mining Classification

2020-01-22abs ↗pdf ↗

PrivySense:

\underline{Pri}

\underline{V}

olatilit

\underline{y}

based

\underline{Sen}

timent

\underline{s}

\underline{E}

stimation from Financial News using Machine Learningq-fin.CP

As machine learning ascends the peak of computer science zeitgeist, the usage and experimentation with sentiment analysis using various forms of textual data seems pervasive. The effect is especially pronounced in formulating securities trading strategies, due to a plethora of reasons including the relative ease of imp…

2017-12-30abs ↗pdf ↗

Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Networkcs.CL

Paper benchmarks Bengali language classification tasks using MConv-LSTM network.

problem Lack of computational resources for NLP tasks in under-resourced languages like Bengali.

method Built three datasets, BengFastText word embeddings, and MConv-LSTM network for hate speech detection, document classification, and sentiment analysis.

result BengFastText yields up to 92.30%, 82.25%, and 90.45% F1-scores in document classification, sentiment analysis, and hate speech detection respectively.

Bengali Multichannel Convolutional-LSTM Hate Speech Sentiment Analysis Document Classification

2020-04-11abs ↗pdf ↗