CS297 Proposal

Description:

Yioop is an open source web portal that has a search engine, a wiki system, and discussion board. Currently, Yioop uses a collaborative filtering media job to suggest discussion groups and discussion threads to users. Recently, a previous master's students, Anirudh Mallya, modified how the vectors for this system are calculated to use a hash2vec approach. Our projects aims to fully incorporate his system into Yioop and to extend it so that suggestions for Wiki pages and resources on wiki pages such as videos are also offered to the users. Another extension we will attempt is to use collaborative filtering on user searches in creating search result rankings.

Schedule:

Deliverables:

The full project will be done when CS298 is completed. One of the goals of CS 297 is understand the Yioop code base. To that end, Tthe following will be done by the end of CS297:

1. Add an Emoji Picker tool to the Messages activity in Yioop.

2. Add at least five UI unit tests to Yioop.

3. Update the Manage Activity in Yioop so that unused credits can be converted back to real cash or cryptocurrencies

4. Rework Anirudh's hash2vec patch so that it can be incorporated into Yioop.

5. CS 297 Report

References:

[1]   M. Chiang,  Networked Life.  New York, NY: Cambridge University Press, 2012.

[2]   F. Xue, X. He, X. Wang, J. Xu, K. Liu and R. Hong, "Deep Item-based Collaborative Filtering for Top-N Recommendation," presented at the ACM Transactions on Information Systems, Aug 2018.

[3]   J. B. Schafer, D. Frankowski, J. Herlocker and S. Sen, "Collaborative Filtering Recommender Systems," The Adaptive Web, Lecture Notes in Computer Science, vol 4321. Springer, Berlin, Heidelberg. DOI:https://doi.org/10.1007/978-3-540-72079-9_9.

[4]   X. Li, D. Li, "An Improved Collaborative Filtering Recommendation Algorithm and Recommendation Strategy," Mobile Information Systems, vol. 2019, Article ID 3560968, 11 pages, 2019. DOI:https://doi.org/10.1155/2019/3560968.