As an AI language model, I can analyze the movie taste based on the given rating history. Here are the TASTE-REASON pairs for the movies:

TASTE: Classic Sci-Fi
REASON: I rated movies like Alphaville, Star Trek: The Wrath of Khan, and Starman highly, indicating my preference for classic science fiction films.

TASTE: Cult Classics
REASON: I gave high ratings to movies like Alan Smithee Film: Burn Hollywood Burn and Idiots, The (Idioterne), suggesting my appreciation for unconventional and offbeat films.

TASTE: Musical Drama
REASON: Evita and Victor/Victoria received high ratings from me, indicating my affinity for musical dramas.

TASTE: Quirky Comedy
REASON: High Fidelity and Men in Black, which I rated highly, suggest my fondness for movies that blend comedy with unique and eccentric elements.

TASTE: Psychological Thriller
REASON: Ravenous and Poltergeist, which received high ratings from me, indicate my interest in psychological thrillers and horror films.

TASTE: Cult Horror
REASON: Halloween and The Thing, both of which I rated highly, suggest my preference for cult horror movies.

Now, let's analyze the user's tendencies for high and low ratings:

HIGH RATINGS: The user tends to give high ratings (above 3) to classic sci-fi, cult classics, musical dramas, quirky comedies, psychological thrillers, and cult horror movies.

LOW RATINGS: The user tends to give low ratings (below 2) to movies that do not fall into the genres mentioned above.

Please note that these conclusions are based solely on the given rating history and may not accurately represent the user's complete movie taste.