PapersResearch

Research Projects

Data mining, text analytics, machine learning, econometrics, and GIS as instruments for reading social and spatial systems.

Two studies on markets, media, tourism, and place.

Research on the Influence of Social Media upon the Stock Market Based on Data Mining

Analysed and predicted the stock market using big data from social media by means of web crawler technology, text mining technology, machine learning algorithms, and econometric methods.

Applied natural language processing and sentiment analysis to handle unstructured social media texts and build an emotion index. Using linear regression and neural network in deep learning, it empirically studied stock market performance, continuously monitored social media's impact, and provided investment advice and forecasts based on social media fluctuations.

Documents Chinese Version (PDF) English Version (PDF)

Sino-Russian Geoscience Field Expedition and Research Program at Lake Baikal

Participated in a Sino-Russian geoscience field study at Lake Baikal, conducting research on Chinese tourists' spatial-temporal distribution via big data crawling, text analytics, and GIS mapping to assess tourism capacity and development needs.

Documents Chinese Version (PDF) English Version (PDF)

Research Methodologies

The projects combine computational collection, language analysis, statistical modeling, and spatial visualization to connect digital traces with real-world behavior.

  • Big Data Analysis: Web crawling and large-scale data processing
  • Text Mining: Natural language processing and sentiment analysis
  • Machine Learning: Classification algorithms and neural networks
  • Econometric Analysis: Statistical modeling and time series analysis
  • GIS Visualization: Spatial-temporal mapping and analysis

Technology Stack

The work uses a mixed toolkit across programming, data processing, deep learning, text analysis, visualization, and econometrics.

Programming Languages

  • Python (Data analysis, Machine learning)
  • R (Statistical analysis)
  • SQL (Database queries)

Main Tools and Frameworks

  • Data Processing: Pandas, NumPy, Scikit-learn
  • Deep Learning: TensorFlow, Keras, LSTM
  • Text Analysis: NLTK, jieba, Sentiment dictionaries
  • Visualization: Matplotlib, Seaborn, GIS platforms
  • Econometrics: SPSS, Stata, VAR models

Data Sources

The datasets bridge online behavior, financial movement, tourism platforms, and market indicators.

  • Twitter API (Social media data)
  • Yahoo Finance (Stock market data)
  • Major tourism platforms (User reviews and travel blogs)
  • S&P 500 Index data

Key Findings

The findings show how social signals can anticipate financial volatility, and how tourism demand can outpace regional capacity.

Social Media and Stock Market Research

  • Machine learning algorithms achieved 88% accuracy in sentiment analysis, far exceeding traditional sentiment dictionary methods.
  • Social media sentiment indices show significant negative correlation with stock market volatility.
  • LSTM neural networks outperform traditional linear regression models in stock prediction.
  • Social media sentiment demonstrates short-term predictive capability for stock markets.

Lake Baikal Tourism Research

  • Chinese tourist numbers have grown significantly, but local tourism capacity is insufficient.
  • Irkutsk serves as a crucial transit hub in tourism development.
  • Lagging infrastructure development is the main constraint on tourism growth.
  • Need to balance tourism development with environmental protection.