Data Sources编程辅导、讲解R程序语言、R编程讲解
- 首页 >> Java编程 The final essay can be based on any of the following sources of data:
The dataset used for your EM777 group project
The 2020 US Presidential Election dataset can be downloaded from the course
GitHub repository
o https://github.com/tj-cahill/em797
o [GitHub -> data -> election.xlsx]
Requirements
*10-12 pages, APA format
Using one of the datasets above, you can structure your final SNA paper as follows:
1. Background and Research Questions/Hypotheses: must be SNA-related (2 pages)
Students are encouraged to ask research questions that we have discussed throughout
this course, for example: node/actor position, tie strength, formation of communities,
mechanism of social interaction, homophily of networks, etc.
The research questions or hypotheses may be descriptive or inferential, and may
include what, how, and why questions.
RQs and hypotheses should be proposed and examined in light of existing literature.
You should also briefly describe the study context and social background associated
with your research topic.
2. Your Data Nature: What does it involve? What does it look like? Why it might be useful
to address your research questions (1 page)
Describe the basic information of your social data, including, but not limited, the
number of participants, the number of activities, types of relations, and variables that
matter to your study.
Describe how you present your data and how it is organized.
Explaining how the dataset can be used to answer your research questions and
hypotheses.
3. Data Wrangling: How do you pre-process and convert your data into network objects? (1
page)
A brief description of data cleaning and data wrangling.
To this end, each operation should be presented in a R markdown file, along with
clear annotations, programming codes, and executed results.
The variables you will be using in your analysis must be defined appropriately
according to your study context.
4. Describing Your Networks (1 page)
Describe the characteristics of your overall networks, such as the number of nodes,
the number of edges, diameters, etc.
You can also describe your network in terms of its social implications. You may want
to consider, for example, the types of social preferences or patterns of online behavior
your network exhibits, the social trend your network represents, or the divisive
communities your network encompasses.
Your portrayals of your network should be linked to social realities and you should
explain what the network represents or really means in the context of your research.
If applicable, the procedures for describing your networks should be included in your
R markdown file.
5. Quantifying Your Networks (1-2 page)
Measuring your network(s) using SNA metrics.
Using what you've learned from lectures and labs, you can focus on actor-level
metrics, global-level metrics, or both at once.
It is essential to specify conceptually and operationally the metrics that will be used in
your study and explain the rationale of quantifying your networks to answer your
research questions and hypotheses.
If applicable, the steps of quantifying your networks and the functions and results of
calculating each metric must be included in your R markdown file.
6. Statistical Analysis (1-2 pages, optional)
Conducting appropriate statistical analyses to address your research questions or
hypotheses.
The results of the study should be reported in the final essay, just like in a regular
research paper.
If applicable, procedures for the statistical analysis must be included in the R
markdown file.
7. Visualization (1-2 pages)
You can visualize networks using either Gephi or R.
You may also include tables, figures, or other visuals in your essay.
You need to interpret visuals embedded in the context of your study and relate them
back to your RQ and hypotheses.
When using R to create visuals, data visualization steps must be included in R
markdown files.
8. Interpretations and Reflections (1-2 pages)
Comparable to the discussion, conclusion, and limitation sections of a regular
research paper.
Additional Notes:
This final essay can be seen as a culmination of all the lab assignments you have completed but
led by your proposed research question(s) and the context of your research.
In this essay, instead of driving by a specific research question or a theory, you can choose to
write a “data-driven” paper. In other words, you can explore your data and come up with a
research question or hypotheses for your study that fit the analyses and results of your data - and
so on until you are able to tell a coherent story that ties your theory to your data.
Your essay and R markdown file (convertible to PDF format) must be submitted together.
R markdown [data + R scripts + explanations = computational essay]
Your R markdown doesn't have to be a well-written computational essay, but it
should include each of the steps of codes in chunks, basic annotations, and the
computed results.
The dataset used for your EM777 group project
The 2020 US Presidential Election dataset can be downloaded from the course
GitHub repository
o https://github.com/tj-cahill/em797
o [GitHub -> data -> election.xlsx]
Requirements
*10-12 pages, APA format
Using one of the datasets above, you can structure your final SNA paper as follows:
1. Background and Research Questions/Hypotheses: must be SNA-related (2 pages)
Students are encouraged to ask research questions that we have discussed throughout
this course, for example: node/actor position, tie strength, formation of communities,
mechanism of social interaction, homophily of networks, etc.
The research questions or hypotheses may be descriptive or inferential, and may
include what, how, and why questions.
RQs and hypotheses should be proposed and examined in light of existing literature.
You should also briefly describe the study context and social background associated
with your research topic.
2. Your Data Nature: What does it involve? What does it look like? Why it might be useful
to address your research questions (1 page)
Describe the basic information of your social data, including, but not limited, the
number of participants, the number of activities, types of relations, and variables that
matter to your study.
Describe how you present your data and how it is organized.
Explaining how the dataset can be used to answer your research questions and
hypotheses.
3. Data Wrangling: How do you pre-process and convert your data into network objects? (1
page)
A brief description of data cleaning and data wrangling.
To this end, each operation should be presented in a R markdown file, along with
clear annotations, programming codes, and executed results.
The variables you will be using in your analysis must be defined appropriately
according to your study context.
4. Describing Your Networks (1 page)
Describe the characteristics of your overall networks, such as the number of nodes,
the number of edges, diameters, etc.
You can also describe your network in terms of its social implications. You may want
to consider, for example, the types of social preferences or patterns of online behavior
your network exhibits, the social trend your network represents, or the divisive
communities your network encompasses.
Your portrayals of your network should be linked to social realities and you should
explain what the network represents or really means in the context of your research.
If applicable, the procedures for describing your networks should be included in your
R markdown file.
5. Quantifying Your Networks (1-2 page)
Measuring your network(s) using SNA metrics.
Using what you've learned from lectures and labs, you can focus on actor-level
metrics, global-level metrics, or both at once.
It is essential to specify conceptually and operationally the metrics that will be used in
your study and explain the rationale of quantifying your networks to answer your
research questions and hypotheses.
If applicable, the steps of quantifying your networks and the functions and results of
calculating each metric must be included in your R markdown file.
6. Statistical Analysis (1-2 pages, optional)
Conducting appropriate statistical analyses to address your research questions or
hypotheses.
The results of the study should be reported in the final essay, just like in a regular
research paper.
If applicable, procedures for the statistical analysis must be included in the R
markdown file.
7. Visualization (1-2 pages)
You can visualize networks using either Gephi or R.
You may also include tables, figures, or other visuals in your essay.
You need to interpret visuals embedded in the context of your study and relate them
back to your RQ and hypotheses.
When using R to create visuals, data visualization steps must be included in R
markdown files.
8. Interpretations and Reflections (1-2 pages)
Comparable to the discussion, conclusion, and limitation sections of a regular
research paper.
Additional Notes:
This final essay can be seen as a culmination of all the lab assignments you have completed but
led by your proposed research question(s) and the context of your research.
In this essay, instead of driving by a specific research question or a theory, you can choose to
write a “data-driven” paper. In other words, you can explore your data and come up with a
research question or hypotheses for your study that fit the analyses and results of your data - and
so on until you are able to tell a coherent story that ties your theory to your data.
Your essay and R markdown file (convertible to PDF format) must be submitted together.
R markdown [data + R scripts + explanations = computational essay]
Your R markdown doesn't have to be a well-written computational essay, but it
should include each of the steps of codes in chunks, basic annotations, and the
computed results.