Analyzing the Impact of Songs, Backgrounds, and Fonts on Instagram Reel Views

Based on @thorfinn_wisdom's content (Batch V1)

---

Intro

In this short analysis, we explore how video production choices, specifically the song used, background visuals, and font style influence the performance of Instagram Reels from the creator @thorfinn_wisdom. Check out the content of the account to get a better gauge of the content being analyzed.

The dataset consists of 93 videos, with each video using one of several possible background visuals and one of several possible songs. The variable of interest is videoPlayCount which is the number of views a Reel receives.

To quantify the effects of these creative choices, we ran a multilinear regression, where each song and background is represented by a dummy variable (1 if used in the video, 0 otherwise). Font choice was also included with Roboto-Regular as one dummy; where Roboto-Medium serves as the reference baseline.

---

Method

A multilinear regression model was used:

videoPlayCount = β₀ + Σ βᵢ * Songᵢ + Σ βⱼ * Backgroundⱼ + βₖ * Font + ε

• Dependent variable: videoPlayCount
• Independent variables:
  • Dummy variables for songs
  • Dummy variables for backgrounds
  • Dummy variable for font
• Reference categories:
  • The song and background not shown in the regression table (implicitly captured by the intercept).
  • For font, Roboto-Medium is the reference.

Note: New backgrounds were introduced at a later point, hence half the sample(around 45 reels) had the chance of using more video backgrounds. The most commonly used background was vin6(13.9% of videos) and the least used vin14 and vin15(3.2%). The most commonly used background songs were bossavibez and springtheme(12.9%) and the least used was thorfinn1.

---

Results

Overall Model Fit

• R-squared: 0.269 → About 27% of the variation in videoPlayCount is explained by the model.
• Adjusted R-squared: 0.012 → Adjusted for model complexity, relatively low explanatory power.
• F-statistic p-value: 0.427 → The overall model is not statistically significant at conventional levels.

While individual variables may show interesting patterns, the model as a whole is exploratory and not predictive.

Song Effects

Top 3 Most Positive Song Coefficients:

1️⃣ song_name_thorfinn2.mp3: +426.52 views (p = 0.023, statistically significant)

2️⃣ song_name_thorfinn1.mp3: +88.78 views (p = 0.638)

3️⃣ song_name_thorfinn3.mp3: +56.35 views (p = 0.704)

Top 3 Most Negative Song Coefficients:

1️⃣ song_name_bossalowed.wav: -73.16 views (p = 0.646)

2️⃣ song_name_tavernahoy.wav: +18.55 views (but still small effect; p = 0.909)

3️⃣ song_name_springtheme.wav: +5.83 views (essentially neutral; p = 0.969)

Insights:

The standout result is song_name_thorfinn2.mp3, which shows a large positive and significant effect on video views. This suggests it may be a particularly engaging or well-matched audio track for this audience. Scroll to the bottom to listen to the tracks.

Other songs show non-significant coefficients, meaning we should not place much confidence in their individual effects.

Background Effects

Top 3 Most Positive Background Coefficients:

1️⃣ background_vin12.mp4: +356.24 views (p = 0.108)

2️⃣ background_vin15.mp4: +82.69 views (p = 0.731)

3️⃣ background_vin9.mp4: +43.99 views (p = 0.840)

Top 3 Most Negative Background Coefficients:

1️⃣ background_vin5.mp4: -164.24 views (p = 0.408)

2️⃣ background_vin14.mp4: -84.96 views (p = 0.728)

3️⃣ background_vin10.mp4: -60.10 views (p = 0.773)

Insights:

• background_vin12.mp4 appears to be a promising background with a large positive coefficient, though not statistically significant at the 5% level (p = 0.108).
• background_vin5.mp4 shows the most negative effect, suggesting this background might be underperforming visually.

However, none of the background coefficients are significant, hence these patterns are suggestive but not conclusive.

Font Effect

Roboto-Regular.ttf: +79.82 views (p = 0.281)

→ Slight positive coefficient, not statistically significant.

Summary of Significance

• Only one variable(song_name_thorfinn2.mp3), shows a statistically significant effect (p < 0.05).
• Other variables display interesting patterns but are not statistically distinguishable from zero.

---

Conclusion

Key Takeaways:

✅ song_name_thorfinn2.mp3: Videos using this song tend to receive significantly more views.

✅ background_vin12.mp4: While not statistically significant, it shows a large positive coefficient. Further testing is needed.

🚫 background_vin5.mp4: Associated with lower views, albeit not statisticlly significant.

Cautions:

• The model’s overall explanatory power is weak and not significant.
• Most effects are not statistically significant and hence results should be treated as exploratory rather than definitive.
• Larger sample sizes and possibly interaction terms (song × background) could improve understanding.
• A casual relationship is argiably present given statistical significance, although omitted variable bias could still plays a role.