MM325M5_Project_part4
docx
keyboard_arrow_up
School
Indiana University, Bloomington *
*We aren’t endorsed by this school
Course
M781
Subject
Communications
Date
Apr 3, 2024
Type
docx
Pages
5
Uploaded by pkothako
MM325M5: Project Part 4
Text mining is a thriving avenue of qualitative data analysis. The process of transforming unstructured text into a structured format to glean patterns and new insights is part of improving decision-making of any organization. Its applications extend
broadly, for example, from ads using popular idioms, or slang, targeted to consumers in particular regions of the country to graphical illustrations of frequently expressed themes
in a sequence of social media posts.
Perspectives on our changing demographics can be studied as we have seen in previous discussions. Cultural perspectives of social inequities can be gathered in various forms. Sometimes social inequities are experienced first-hand, covered in news and media, and often depicted in art. Some broad examples include racial bias in the news coverage, gender inequality in certain professions, absence of diverse representation in various fields, racial/gender/age bias in patient healthcare, and lack of basic services in lower socioeconomic areas. How a society confronts inequities largely depends on public opinion and is often influenced by news.
Your organization has put you to the task of investigating recent articles from media sources to extract verbiage patterns in their publications. You will implement techniques
to statistically mine text in order to complete this project.
MM325 Project Part 4:
●
Project Description: Write a report of how your analysis would be performed, introducing your readers (i.e., other staff at your non-profit) to the topic, to the articles you sourced, and from what sources they were obtained. In the report, you should:
○
Write an introduction which includes references to at least 3 articles where
information can be found about the topic.
○
Describe how at least three text mining analysis can be constructed, citing
the sources used to build your understanding of the analysis and to develop the code for creating the visualizations.
○
Explain what the output for each of the three (or more) unique text mining techniques is intended to reflect about the text.
○
For each visualization technique, describe how a positive or negative outcome would be identified.
○
The conclusion should also include reflections on how text mining would be practical for this analysis and how it may be a useful analysis technique
in other contexts. ○
Cite all news articles and R
coding resources on a separate References page, and include all graphical content on separate pages at the end of your report, following APA guidelines. You may save your report as a Word document (.docx) or PDF file (.pdf).
Project Guide
Professional, written reports should include an introduction, body, and conclusion, as well as citations to referenced material. As you plan your written content for this project, it is recommended that you first outline the organization of the content, including at least
three specific ideas you want to discuss in the body of your report. As you develop graphics and output from your analysis in R
, you can write a first draft of the introductory
paragraph, at least three body paragraphs, and your concluding paragraph(s). Then, once you finalize your analysis using R
, you may revise your first draft to clearly express
your analysis and address all of the objectives for the Project Report, as outlined in the Project rubric.
Your report should include a highly developed purpose and viewpoint; it should also be written in Standard English and include appropriate content, organization, style, grammar, and mechanics. There should be no evidence of plagiarism
. If you are unsure about what constitutes plagiarism, please review the plagiarism policy. Your report, including references, must use proper APA format. You can find APA resources in the Academic Success Center Reference Library on the Research, Citation, and Plagiarism page
.
**MM325 Project Part 4: Gender Pay Gap Analysis Report**
**Introduction**
The gender pay gap remains a persistent issue worldwide, reflecting systemic inequalities in the workforce. Despite advancements in gender equality, women, on average, still earn less than men in many professions and industries. This report aims to
analyze recent articles from media sources to extract verbiage patterns related to the gender pay gap. The articles were sourced from reputable news outlets and analyzed using text mining techniques to uncover insights into societal perspectives, discussions, and potential solutions regarding this issue.
**Articles Used for Analysis**
1. "The Gender Pay Gap: What Women Need to Know" - Forbes
2. "Closing the Gender Pay Gap: Progress and Challenges" - Harvard Business Review
3. "Understanding the Gender Pay Gap: Causes and Solutions" - The New York Times
**Text Mining Analysis Techniques**
1. **Word Frequency Analysis**:
- This technique involves counting the frequency of words appearing in the articles. Commonly used libraries in R, such as `tm` and `tidytext`, can be utilized for this analysis.
- The output reflects the most frequently mentioned terms related to the gender pay gap, providing insights into the key topics and themes discussed in the articles.
- Positive outcomes would include terms such as "equal pay," "gender parity," and "fair compensation," indicating a focus on addressing the issue. Negative outcomes
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help
might involve terms like "discrimination," "wage gap," and "inequality," highlighting the challenges and disparities present.
2. **Sentiment Analysis**:
- Sentiment analysis evaluates the sentiment or tone of the text, determining whether it is positive, negative, or neutral. This can be achieved using sentiment lexicons and machine learning algorithms.
- The output reveals the overall sentiment towards the gender pay gap discussion in the articles. Positive sentiment indicates optimism or progress, while negative sentiment
suggests frustration or dissatisfaction.
- Positive outcomes would be reflected in articles with sentiments conveying hopefulness, progress, or advocacy for change. Conversely, negative outcomes might involve sentiments expressing anger, disillusionment, or resignation regarding the issue.
3. **Topic Modeling**:
- Topic modeling identifies latent topics within a corpus of text documents. Techniques
such as Latent Dirichlet Allocation (LDA) can be applied to extract these topics.
- The output displays clusters of words representing different topics discussed in the articles. Each topic provides insight into specific aspects of the gender pay gap discourse.
- Positive outcomes involve topics centered around solutions, progress, and empowerment. Negative outcomes may include topics related to discrimination, barriers, and disparities.
**Conclusion**
Text mining provides a powerful tool for analyzing large volumes of text data efficiently and extracting valuable insights. In the context of the gender pay gap, it enables organizations to understand prevailing attitudes, identify key issues, and track progress towards gender equality. Positive outcomes in the analysis indicate a proactive approach towards addressing inequalities, while negative outcomes highlight persistent challenges that require attention. Beyond gender pay gap analysis, text mining can be applied to various contexts, including sentiment analysis of customer feedback, topic modeling in academic research, and trend analysis in social media monitoring.
**References**
Articles:
1. [Article 1]
2. [Article 2]
3. [Article 3]
R Coding Resources:
1. "Text Mining with R: A Tidy Approach" by Julia Silge and David Robinson
2. "Text Mining in Practice with R" by Ted Kwartler and Josh Katz
**Graphical Content**
[Insert graphical content pages following APA guidelines]
---
Note: Please replace [Article X] with the proper APA citation for each article.