Surveys without Questions: A Reinforcement Learning Approach

Authors: Atanu R Sinha, Deepali Jain, Nikhil Sheoran, Sopan Khosla, Reshmi Sasidharan257-264

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental On validation against actual survey data, proxy ratings yield reasonable performance results. The dataset is split randomly into two groups for training (75%) and testing (25%).
Researcher Affiliation Industry 1Adobe Research, India 2Adobe, India atr@adobe.com, jaindeepali@google.com,{sheoran, skhosla, rsasidha}@adobe.com
Pseudocode No The paper describes the methods using mathematical equations and text, and includes a diagram (Figure 1), but does not present structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statement about releasing source code or provide a link to a code repository.
Open Datasets No The paper states, "Clickstream data from the website of a consumer electronics company are used," indicating proprietary data without providing any public access information, links, or citations for the dataset.
Dataset Splits Yes The dataset is split randomly into two groups for training (75%) and testing (25%).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions using an LSTM model and RNN, but does not provide specific software names with version numbers for dependencies (e.g., 'TensorFlow' or 'PyTorch' with versions).
Experiment Setup No The paper mentions a fixed dimension of 150 chosen based on limited hyper-parameter tuning (50, 100, 150, 200) for state representation, and refers to a 'learning rate' (alpha) but does not provide specific values for these or other hyperparameters like batch size, epochs, or optimizer settings.