Sole Pera, Ph.D.

Boise State University | solepera@boisestate.edu

ABOUT

After completing her Ph.D. in Computer Science at Brigham Young University in 2014, Dr. Maria Soledad Pera, a native of Argentina, joined Boise State University as an Assistant Professor in the Department of Computer Science. Sole's main area of expertise is in information retrieval and her current research work focuses on the application of information retrieval, information extraction, and natural language processing techniques for developing recommendation systems, primarily for children.

Research Interest: Information Retrieval, Recommender Systems, Web Search, System Analysis, Information Extraction, Machine Learning, Databases, Data Mining, Natural Language Processing.

EDUCATION

PhD in Computer Science
Brigham Young University, Provo, Utah, USA
Proposed Dissertation Topic: “Using Online Data Sources to Make Recommendations on Reading Materials for K-12 and Advanced Readers” – Advisor: Dr. Yiu-Kai Ng

April 2014 

M.S. in Computer Science 
Brigham Young University, Provo, Utah, USA 
Thesis: “Improving Library Searches Using Word-Correlation Factors and Folksonomies” – Advisor: Dr.Yiu-Kai Ng

April 2009

B.S. in Information Systems Analysis 
Universidad Tecnologica Nacional, Rosario, Argentina

September 2006

CLASSES THAT I TEACH

CS 361 – Introduction to the Theory of Computation

Fall 2014, Fall 2015, Spring 2016, Summer 2016

CS 597 – Special Topics: Information Retrieval 

Spring 2015

CS 497 – Introduction to Information Retrieval 

Fall 2016

CURRENT ACTIVITIES

ACM-W Boise State University  -  Faculty Advisor

ReleventCity  -  Advisor 

The 3rd International Workshop on Educational Recommender Systems (EdRecSys)  -  Co-Chair 

Collaboration with BookItForward, a community organization focused on increasing access to books.

CURRENT GRADUATE STUDENTS

Nevena Dragovic  Curating Recommendations to Satisfy Users’ Needs and Expectations

Ion Madrazo Azpiazu  First Steps Towards Multilingual Readability Assessment

Jason Hall

Oghenemaro Anuyah

Jennifer Eckstrand

FORMER GRADUATE STUDENTS

Axel Magnuson   Evaluation of Topic Models for Content-Based Popularity Prediction on Social Microblogs

Deepa Mallela   CEST: City Event Summarization using Twitter

CURRENT UNDERGRADUATE STUDENTS

Daniel Bakyono

CURRENT RESEARH

Recommendation Systems

Recommendation-based book exchanged system based on users' item lists.

Polarity-neutral recommendations based on ratings and reviews generated by a user to learn the item characteristics that are most likely appealing to the user.

Readability Assesment

Multilingual Readability Assessment based on the well known supervised learning techniques from the machine learning field, it makes use of hundreds of features created using Natural Language Processing methods for predicting the level of complexity of an input text.

Web Environment for Children

Designing modules to enhance web search environment tailored towards children by developing query suggestions and query recommendation modules, together with a search environment that filters resources by the readability level of each young user.

RECENT PUBLICATIONS

Sean MacLachlan, Nevena Dragovic, Stacey Donohue and Maria Soledad Pera. "One Size Doesn’t Fit All: Helping Users Find Events from Multiple Perspectives". In Proceedings of the ACM RecSys Workshop on Recommenders in Tourism, Boston, USA, September 2016.

Stacey Donohue, Nevena Dragovic, and Maria Soledad Pera. "Anything Fun Going On? A Simple Wizard to Avoid the Cold-Start Problem for Event Recommenders". In Proceedings of the ACM RecSys Workshop on Recommenders in Tourism, Boston, USA, September 2016.

Ion Madrazo and Maria Soledad Pera. "Is Readability a Valuable Signal for Hashtag Recommendations?". In Proceedings of the ACM Conference on Recommender Systems (ACM RecSys 2016) - Poster, Boston, USA, September 2016.

Nevena Dragovic and Maria Soledad Pera. "Genre Prediction to Inform the Recommendation Process". In Proceedings of the ACM Conference on Recommender Systems (ACM RecSys 2016) - Poster, Boston, USA, September 2016.

Ion Madrazo Azpiazu, Nevena Dragovic, and Maria Soledad Pera. "Finding, Understanding and Learning: Making Information Discovery Tasks Useful for Children and Teachers". In Proceedings of ACM SIGIR Workshop on Search as Learning. Pisa, Italy, July 2016.

Nevena Dragovic, Ion Madrazo, and Maria Soledad Pera. ""Is Sven Seven?": A Search Intent Module for Children". In Proceedings of the 39th International ACM SIGIR Conference, Pisa, Italy, July 17-21, 2016.

Joel Denning, Maria Soledad Pera, and Yiu‐Kai Ng. "A readability level prediction tool for K‐12 books." Journal of the Association for Information Science and Technology, 2015.

Meher Shaikh, Maria Soledad Pera, and Yiu-Kai Ng, Suggesting Simple and Comprehensive Queries to Elementary-Grade Children. To appear in Proceedings of the IEEE/WIC/ACM Conference on Web Intelligence (WI'15), Singapore, December 6-9, 2015.

Nevena Dragovic and Maria Soledad Pera. Exploiting Reviews to Guide Users’ Selections. In Proceedings of the 9th ACM Conference on Recommender Systems (ACM RecSys 2015) - Poster, Vienna, Austria, September 16-20, 2015.

Maria Soledad Pera and Yiu-Kai Ng, A Recommendation-Based Book-Exchange System Without Using Wish Lists. In Proceedings of the 9th ACM Conference on Recommender Systems (ACM RecSys 2015) - Poster, Vienna, Austria, September 16-20, 2015.

Shahrzad Karimi and Maria Soledad Pera. Recommendations to enhance Children Web Searches. In Proceedings of the 9th ACM Conference on Recommender Systems (ACM RecSys 2015) - Poster, Vienna, Austria, September 16-20, 2015.

Maria Soledad Pera and Yiu-Kai Ng, Analyzing Book-Related Features to Recommend Books for Emergent Readers. In Proceedings of the 26th ACM Conference on Hypertext and Social Media (ACM HT 2015), pp. 221-230, Cyprus, September 1-4, 2015.

Full Publication List



Funded Projects

IR for Children: Enhanced Search Environment for Children (CRII: III: Children and Information Retrieval Tasks: Search Intent, Query Suggestions, and Adequate Online Resources )

Abstract: Children are introduced to the Web at increasingly young ages. While early exposure can help them build foundational skills vital in a knowledge-rich society, search tools were not designed with children in mind nor do retrieved results explicitly target children. Most engines do not support children's inquiry approaches (or do not support them well) and typically do not return content suitable to children's interests or reading levels. This need is important to address given that early experiences can affect attitudes in using the Web, skill development in making adequate use of resources for personal and educational interests, and the ability to leverage information and use it to make contributions into adulthood. The PI and her team will design and develop software modules as search engine add-ons to meet the needs of children searching the Web. The modules, which will upgrade current computation infrastructure, will be domain-independent, tailored to children, and usable on Google, to locate child-friendly educational- and leisure-related information. Research outputs will facilitate children's engagement with technology by improving their interactions on the Web. Partnerships with Idaho K-9 classrooms will allow the research team to gather feedback from children and teachers and verify the usefulness of the proposed modules in their intended, formal setting.
More information: Working Toward a Better, Kid-Friendly Search Engine



CONTACT

Email
solepera@boisestate.edu

Address
1910 University Dr. 
Boise, ID 83725
Office: CCP 354

Phone
208-426-2487