ACCENTURE VIRTUAL INTERNSHIP

I’m very excited to share with you that I just completed a virtual internship project provided by Accenture.

Accenture is a global professional services company, and it has a significant presence in North America. Specializing in consulting, technology, and outsourcing services, Accenture works with clients across various industries to help them improve their performance and achieve their business objectives.

Data Used

1. Dataset was provided by the Industrial Expert of Accenture.

2. Data contains 7 dataset ( User, Profile, Location, Session, Content, Reaction, Reaction Types ) , each data contains different columns and values.

Task 1 : Business Questions

1. Top 5 categories with the largest popularity.
2. How many unique categories are there ?
3. How many reactions are there to the most popular categories ?
4. What was the month with most post ?

Project Understanding

I work as a Data Analyst at Accenture, I work within a larger team, where each member has a different role and level of responsibility and My team has been assigned a new project for a client called Social Buzz.

Summary of my Team

1. Industry Experts : This is the social media space to ensure I accurately understand Social Buzz sector.
2. IPO Experts : Who will deliver on IPO requirement.
3. Data Expert : Who will provide Big Data insights and content category analysis. This is where I sit.

Key Roles and Responsibility of a Data Analyst

A data analyst sits between the business and the data.

What do I mean by that?

• The Business refers to the client and your internal team members who won’t be involved in detailed data analysis.
• They rely on my analysis to make strategic business decisions.
• The Data refers to the relevant data sources that will be clean, process, and use to generate interesting insights for the business.

Task 2 : Data cleaning and Modeling

Data Modeling

Step 1 : select the Dataset needed for the Business Question to do this i have to use Data Model to identify which dataset will be required to answer the Business question.

Reaction, Content , and Reaction Types

To clarify why I made this selection:

• The brief carefully it states that the client wanted to see “An analysis of their content categories showing the top 5 categories with the largest popularity”.
• popularity is quantified by the “Score” given to each reaction type.
• I therefore need data showing the content ID, category, content type, reaction type, and reaction score.
• So, to figure out popularity, I have to add up which content categories have the largest score.

Step 2 : Data Cleaning

Data cleaning is a common and very important task when working with data.

What I do

1. I open the three data sets below on Microsoft Excel.
2. Clean the data by:

• removing rows that have values which are missing,
• changing the data type of some values within a column, and
• removing columns which are not relevant to this task.

Create a final data set by merging the three tables together

• I use the Reaction table as base table, then first join the relevant columns from Content data set, and then the Reaction Types data set.
• I use “VLookUp” formula to merge the three tables together.
• The end result to 24,574 rows and 7 columns

Task 3 : Data Visualization

Insights

1. From the data I found a total of 16 unique categories of posts, 24.57k for Total Reaction, 974k for Total Scores, 4 Content Types across sample dataset. This includes things such as Food, Science and Animals. As well as this, there were 1897 reactions from just the animal category alone! People obviously really like animals! And also the most common month for users to post within was January. This aligns with seasonal trends of social media users that feel the need to reconnect with people after calendar events such as Christmas.

2. From my analysis, you can see that the top 5 most popular categories of posts were animals, science, healthy eating, technology and food in descending order. Animals had an aggregate popularity score of around 74965. It is very interesting to see both food and healthy eating within the top 5, it really shows that food is an highly engaging content category. Healthy eating ranks slightly higher than food, so perhaps your user base may be skewed towards healthy eaters and health-conscious people. Finally, its also interesting to see science and technology too. This may suggest that people enjoy consuming factual content and snippets of content that they can learn something from.

3. Distribution of Content Types reveals interesting patterns. Photo lead with 26.41%, closely followed by Video at 25.41%, Gif at 24.7%, and audio content at 23.03%. This breakdown offers valuable insights into the audience preferences for various media formats.

To optimize your content strategy, consider leveraging the popularity of photos and videos. Allocates resources to create visually appealing and engagement photo and videos content . Additionally, monitor audience engagement with gifs and audio content to identify opportunities for improvement or adjustment. This balanced approach can enhanced overall user satisfaction and interaction with your platform.

Conclusion

I tackled this task and found the top 5 most popular categories as asked, but I also went one step further.

I found that animals and science are the two most popular categories, suggesting that users like “real-life” and “factual” content.

I also found that food was a common theme amongst popular content and the most popular food category was healthy eating. This could be a signal to show the types of people that are using the platform, and you could use this insight to boost engagement even further. For example, you could run a campaign with content focused on this category or work with healthy eating brands to promote content.