<?xml version='1.0' encoding='utf-8'?>
<?xml-stylesheet type="text/xsl" href="/v2/static/oai2.xsl"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-10-13T01:42:20Z</responseDate>
  <request identifier="oai:figshare.com:article/34035653" metadataPrefix="oai_dc" verb="GetRecord">https://api.figshare.com/v2/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:figshare.com:article/34035653</identifier>
        <datestamp>2026-09-30T17:36:46Z</datestamp>
        <setSpec>category_7</setSpec>
        <setSpec>category_45</setSpec>
        <setSpec>category_734</setSpec>
        <setSpec>category_931</setSpec>
        <setSpec>category_106</setSpec>
        <setSpec>category_132</setSpec>
        <setSpec>portal_5</setSpec>
        <setSpec>item_type_1</setSpec>
        <setSpec>month_year_09_2026</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"  xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>&lt;p&gt;FNSPID dataset construction workflow showing the parallel collection of textual news articles (via web scraping) and numerical stock price records (via data APIs), followed by temporal alignment and quality control to produce the final integrated corpus.&lt;/p&gt;</dc:title>
          <dc:creator>Hong He (221185)</dc:creator>
          <dc:creator>Xinhai Li (191514)</dc:creator>
          <dc:subject>Medicine</dc:subject>
          <dc:subject>Sociology</dc:subject>
          <dc:subject>Biological Sciences not elsewhere classified</dc:subject>
          <dc:subject>Information Systems not elsewhere classified</dc:subject>
          <dc:subject>Science Policy</dc:subject>
          <dc:subject>Infectious Diseases</dc:subject>
          <dc:subject>three key innovations</dc:subject>
          <dc:subject>strictly chronological train</dc:subject>
          <dc:subject>shape investor behavior</dc:subject>
          <dc:subject>scale temporal fusion</dc:subject>
          <dc:subject>relevant historical patterns</dc:subject>
          <dc:subject>random walk benchmarks</dc:subject>
          <dc:subject>effect size analysis</dc:subject>
          <dc:subject>bootstrap confidence intervals</dc:subject>
          <dc:subject>aware temporal alignment</dc:subject>
          <dc:subject>article without using</dc:subject>
          <dc:subject>ablation studies reveal</dc:subject>
          <dc:subject>2022 &amp;# 8211</dc:subject>
          <dc:subject>2013 &amp;# 8211</dc:subject>
          <dc:subject>time fusion architecture</dc:subject>
          <dc:subject>preventing information leakage</dc:subject>
          <dc:subject>future market information</dc:subject>
          <dc:subject>price autocorrelation vanishes</dc:subject>
          <dc:subject>scale financial news</dc:subject>
          <dc:subject>using large models</dc:subject>
          <dc:subject>time series forecasting</dc:subject>
          <dc:subject>financial news</dc:subject>
          <dc:subject>series models</dc:subject>
          <dc:subject>advanced time</dc:subject>
          <dc:subject>market reaction</dc:subject>
          <dc:subject>level forecasting</dc:subject>
          <dc:subject>financial narratives</dc:subject>
          <dc:subject>series prediction</dc:subject>
          <dc:subject>series data</dc:subject>
          <dc:subject>work demonstrates</dc:subject>
          <dc:subject>text publication</dc:subject>
          <dc:subject>testing ).</dc:subject>
          <dc:subject>test splits</dc:subject>
          <dc:subject>stfa ),</dc:subject>
          <dc:subject>sentiment annotations</dc:subject>
          <dc:subject>semantic information</dc:subject>
          <dc:subject>return prediction</dc:subject>
          <dc:subject>predictive accuracy</dc:subject>
          <dc:subject>multimodal sources</dc:subject>
          <dc:subject>multimodal baselines</dc:subject>
          <dc:subject>liquidity stocks</dc:subject>
          <dc:subject>generated independently</dc:subject>
          <dc:subject>experiments demonstrate</dc:subject>
          <dc:subject>deep learning</dc:subject>
          <dc:subject>based sentiment</dc:subject>
          <dc:subject>balance accuracy</dc:subject>
          <dc:description>&lt;p&gt;FNSPID dataset construction workflow showing the parallel collection of textual news articles (via web scraping) and numerical stock price records (via data APIs), followed by temporal alignment and quality control to produce the final integrated corpus.&lt;/p&gt;</dc:description>
          <dc:date>2026-09-30T17:36:43Z</dc:date>
          <dc:type>Image</dc:type>
          <dc:type>Figure</dc:type>
          <dc:identifier>10.1371/journal.pone.0356139.g003</dc:identifier>
          <dc:relation>https://figshare.com/articles/figure/_p_FNSPID_dataset_construction_workflow_showing_the_parallel_collection_of_textual_news_articles_via_web_scraping_and_numerical_stock_price_records_via_data_APIs_followed_by_temporal_alignment_and_quality_control_to_produce_the_final_integr/34035653</dc:relation>
          <dc:rights>CC BY 4.0</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
