3-way ANOVA with unequal sample sizes (between-groups)

#1
Dear smart people,

I am currently finishing my Master's in International Business Communication and have run into a problem with my data. I was wondering if you guys could maybe offer me some guidance on how to proceed?

For my research, I did the following experiment:

In a between-groups design, two sets of subjects - individuals who are interested in fashion and individuals who are not - were exposed to different treatment conditions: reading one short blog entry that either contained anglicised words or were entirely written in Portuguese (subjects exposed to entries completely written in Portuguese were not exposed to entries that contained anglicised words, and vice-versa).

So, for example, one of my RQs was:

To what extent does the use of anglicisms affect the attitudes towards the author (blogger) among individuals who are interested in fashion and individuals who are not?

I got a total of 564 respondents, however, the sample sizes for each fator were very unequal.

Here's a summary of my independent variables:
LanguageDisplayed" (EN,PT), nEN = 278, nPT = 286
"FashionInterest"(Yes/No), nYES = 401, nNO = 163
Since there were two different sets of texts – one about a black outfit and one about a white outfit -, I included a third independent variable:
“DressColour” (Black/White), nBlack=k = 278, nWhite, n = 286

I ran a 3-way ANOVA and Levene’s test showed a significance of .001, which I hope is to blame on the unequal sample sizes.

I read something about using Brown-Forsythe or Welch’s tests, but did not find a way to run those tests in a 3-way ANOVA. Alternatively, I found something about transforming my data to use weighted values. To be honest, I’m a little lost here. Can anybody help me?

Thank you in advance,
Alana