Synthesizing Aspect-Driven Recommendation Explanations from Reviews
Authors: Trung-Hoang Le, Hady W. Lauw
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on datasets of several product categories showcase the efficacies of our method as compared to baselines based on templates, review summarization, selection, and text generation. |
| Researcher Affiliation | Academia | Trung-Hoang Le and Hady W. Lauw Singapore Management University, Singapore {thle.2017, hadywlauw}@smu.edu.sg |
| Pseudocode | Yes | Algorithm 1 SEER-Greedy; Algorithm 2 Opinion Substitution |
| Open Source Code | No | The paper links to third-party code implementations for EFM and MTER, but does not provide a link or explicit statement for the availability of their own SEER framework's source code. |
| Open Datasets | Yes | Experiments use four public datasets of Amazon reviews1 [Mc Auley et al., 2015] of varying categories: Computer and Accessories (Computer), Camera and Photo (Camera), Toys and Games (Toy), Cell Phones and Accessories (Cellphone). Preprocessing follows [Wang et al., 2018a]. For each category, we retrieve the most common aspects covering 90% of opinion phrases and filter out users and items with fewer than five reviews. The remaining are split into training, validation, and test at a ratio of 0.6 : 0.2 : 0.2 for every user chronologically. Sentences in validation and test with opinions or aspects that had not appeared in training were excluded. Table 2 shows some basic statistics of the datasets. 1http://jmcauley.ucsd.edu/data/amazon/ |
| Dataset Splits | Yes | The remaining are split into training, validation, and test at a ratio of 0.6 : 0.2 : 0.2 for every user chronologically. |
| Hardware Specification | Yes | Experiments were run on machine with Intel Xeon E5-2650v4 2.20 GHz CPU and 256GB RAM. |
| Software Dependencies | No | The paper mentions the use of "CPLEX4 solver" but does not provide a specific version number. It does not list other key software components with version numbers required for replication. |
| Experiment Setup | Yes | For EFM2, as in the original work, the latent factor and explicit factor dimensions are 60 and 40. For MTER, we adopt the default setting of the author s implementation3. ... For ASC2V, we train with similar setting as C2V, using RMSprop for optimization. |