PsyProxy
Datasets·Customer reviews·04__whole_disney_dataset__branch_hk_vs_california

Disneyland reviews: Hong Kong vs California branch

Disneyland Reviews is a public TripAdvisor corpus (Kaggle, Chillar Anand) of 42,656 guest reviews across three Disneyland branches (Paris, California, Hong Kong). The texts predominantly discuss a range of experiences and sentiments related to visits to the amusement park, highlighting both positive and negative aspects. Common themes include ride experiences , with many reviews praising the excitement of various attractions while also noting the long wait times associated with popular rides. Visitors frequently express concerns about costs , mentioning the high prices of food and souvenirs , as well as the overall expense of admission. The cleanliness and staff friendliness are often commended, contributing to a generally positive atmosphere despite complaints about crowds and logistical challenges, particularly for families with young children. Additionally, some reviews suggest strategies for maximizing enjoyment, such as arriving early or utilizing FastPass options to minimize waiting. [Summary on 50 random texts by ChatGPT 4o Mini].

Distribution of Branch (Hong Kong vs California)
1
2
19,406 at floor9,620 at ceiling
29,026
items
5,806
holdout n
Branch (Hong Kong vs California)
target
Binary
kind
24
systems compared
Criterion validity

Reported holdout systems from the verified card

Binary classification uses FVE as the task-primary metric. Secondary columns keep the companion metrics visible so binary, ordinal, regression, and multiclass cards are not compared through one flattened score.

Source podium · FVE · 10 families
Gold
PsyProxy
0.622
Silver
Topic models
0.524
Bronze
LIWC
0.114
Model-family mix
PsyProxy · 4Lexicon · 2Baseline · 15OpenAI / LLM · 3
SystemFamilyVariantFVEAUCF1Primary scale
psyproxyPsyProxy — Health Lens v0.9 · 1100d
PsyProxypermissive0.6220.9540.848
psyproxyPsyProxy — Behavioral Sciences Lens v0.5 · 1000d
PsyProxypermissive0.6220.9540.844
psyproxyPsyProxy — Social Economics Lens v0.5 · 1000d
PsyProxypermissive0.6180.9550.843
psyproxyPsyProxy — Technology Lens v0.5 · 800d
PsyProxypermissive0.5830.9440.834
lexLinguistic Inquiry and Word Count (LIWC)
Lexiconpermissive0.1140.7350.423
baselineTool for the Automatic Analysis of Syntactic Sophistication and Complexity (TAASSC)
Baselinepermissive0.0610.6730.291
baselineTool for the Automatic Analysis of Lexical Sophistication (TAALES)
Baselinepermissive0.0550.6650.227
baselineTextDescriptives
Baselinepermissive0.0340.6330.157
baselineEmpath
Baselinepermissive0.0300.6230.137
llmOpenAI Model gpt-4.1-nano
OpenAI / LLMpermissive0.0170.5880.060
llmOpenAI Model gpt-4o-mini
OpenAI / LLMpermissive0.0160.5850.009
baselineTool for the Automatic Analysis of Cohesion (TAACO)
Baselinepermissive0.0140.5820.014
llmOpenAI Model gpt-5-nano
OpenAI / LLMpermissive0.0120.5720.012
lexValence Aware Dictionary and sEntiment Reasoner (VADER)
Lexiconpermissive0.0010.5250.000
baselineIMDB movie reviews (ACL) binary · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews ordinal · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews continuous · via best lens
Baselinepermissive
baselineAmazon Video-Games reviews binary · via best lens
Baselinepermissive
baselineDruglib drug reviews ordinal · via best lens
Baselinepermissive
baselineSentiment140 tweets binary · via best lens
Baselinepermissive
baselineLIAR fact-check statements ordinal · via best lens
Baselinepermissive
baselineDisneyland TripAdvisor reviews continuous · via best lens
Baselinepermissive
baselineDouban movie reviews (Chinese) ordinal · via best lens
Baselinepermissive
baselineDruglib drug reviews regression · via best lens
Baselinepermissive