溫士朋 | Shih-Peng Wen

熟悉資料收集、數據分析、以及學術寫作。
Tel: 0910-813-930 | E-Mail: [email protected] | Website: wspooong.com |   wspooong

工作經驗

Project Engineer

印度商威普羅 | Jul 2023 - Present

  • 領導測試工具團隊,協助手動測試員設置環境。
  • 進行手動測試以確保硬體和軟體的品質。
  • Dashboard建立:使用 Google Apps Script 追蹤Issue狀態。

資料工程師

中央研究院 人文社會科學研究中心 調查研究專題中心 | Apr 2021 - Jul 2023

  • 研究相關:
    • 網路輿情分析:包含資料清理、文字探勘、NLP等。
    • 調查問卷:規劃問卷,並針對問卷結果進行統計分析及網絡分析。
  • 程式相關:
    • 開發資料爬蟲程式:針對Facebook、YouTube、Twitter、Tiktok開發爬蟲程式。
    • 數據視覺化:利用Python Plotly開發Dashboard供研究案使用。
    • 網頁開發:為協助資料捐贈研究案進行,利用Flask、Vue.js建立資料捐贈工具。
  • 其他:
    • 實習課程規劃:主導為期8週的實習生計畫,協助實習生建立研究問題、利用NLP技術進行研究。

學歷

東海大學| 社會學系 碩士

2016 - 2017, 2019 - 2021 | GPA 3.8
升學結構下的技職教育:以台北市立大安高工為例

世新大學 | 社會心理學系 學士

2012 - 2016

技能

程式語言:Python、R。 | 程式技能:網路爬蟲、資料清理、資料視覺化、SQL、NLP。
研究:內容分析、問卷設計、報告撰寫。 
認證:TOEIC Gold (885/990)、Professional Data Analyst by DataCamp (DA0021135851199)。

專案

NDLTD TW Papers Graph(個人專案)
https://ndltd-tw-papers-graph.wspooong.com/

此專案部署在 AWS 雲端平台上。前端採用 Vue.js,後端使用 FastAPI。Opensearch 作為向量資料庫。透過 GitHub Actions 來自動化 CI/CD 流程。
資料收集部分,使用 AWS Lambda 作為網路爬蟲,並且利用 Sentence-Transformer 來理解文字的含義。文章相似度的判斷,則透過 KNN 演算法來找尋彼此內容相似的文章。

家長的教養焦慮:以文字探勘技術分析「家有中學生」臉書社團(發表於社會學年會)

https://www.tsameetings.org.tw/page.php?menu_id=79&new_id=341

利用BERTopic分析「家有中學生」臉書社團之貼文,觀察各個群集間的趨勢、並試圖解釋。


溫士朋 | Shih-Peng Wen

Python Developer with experience in collecting data, interpreting data and writing.
Tel: 0910-813-930 | E-Mail: [email protected] | Website: wspooong.com |   wspooong

Work Experience

Project Engineer

Wipro
Jul 2023 - Present

  • Leading the testing tool team, assisting manual testers with environment setup.
  • Conducting manual testing to ensure the quality of hardware and software.
  • Building Dashboard for issue tracking with Google Apps Script.

Data Engineer

Center for Survey Research, Research Center for Humanities and Social Sciences, Academia Sinica.
Apr 2021 - Jul 2023

  • Research Experience:
    • Online Opinion Analysis: Conducted data cleaning, text mining (e.g. NLP) for opinion analysis.
    • Survey Design: Planned questionnaires and performed statistical and network analysis on the survey results. 
  • Programming Experience:

    • Web Scraping: Developed web scraper for Facebook, YouTube, Twitter, and TikTok.

    • Data Visualization: Utilized Python Plotly to develop dashboards for research projects.

    • Web Development: Built a data donation tool using Flask and Vue.js for research projects.

  • Other Experience:

    • Internship Program: Led an 8-week internship program, assisting interns in formulating research questions and utilizing text mining techniques for their research.

Education

Tunghai University | M.A, Sociology 

2016 - 2017, 2019 - 2021 | GPA 3.8
Vocational Education Under The Structure Of Credentialism

Shih Hsin University | B.S, Social Psychology

2012 - 2016

Skills

Language: Python, R. | Technical Skills: Web Scraping, Data Cleaning, Visualization, SQL, NLP.
Research Skills: Content Analysis (Qualitative), Survey Design, Academic Writing.
Certifications: TOEIC Gold, Professional Data Analyst by DataCamp (DA0021135851199).

Projects

NDLTD TW Papers Graph (Personal Project)

https://ndltd-tw-papers-graph.wspooong.com/

This project uses Vue.js for the frontend and FastAPI for the backend. It utilizes Opensearch as vector database. The project employs GitHub Actions for automating the CI/CD process. It is hosted on AWS. Uses AWS Lambda as  web scraper to gather data, using Sentence-Transformer to understand the meaning of words, and uses KNN to find articles that are similar to each other.

Parental Parenting Anxiety: Analyzing Facebook Group for Parents of Middle School Students through Text Mining Techniques (Conference Paper)

Agenda

Utilize the OpenAI Embedding model and the Topic Model Method to identify the subjects of discussion among parents on the internet.