My current research project is authorship analysis of the spoken text. I will perform author attribution and verification using text only for various speech datasets. The primary motivation is to identify individual speech styles and distinguish the difference in spoken & written text for the same authors. Also, it will evaluate the quality of spoken texts generated from the LLMs and whether they are on par with the human speakers. 

Publication: [Manuscript submitted recently]

As part of my M.Sc. thesis, I worked on Bengali literature analysis. I have developed a novel word2vec graph method to represent stories as graph structure and utilize this to solve author attribution, genre detection and stylochronometry problem. We also utilize character interaction graphs to answer a wide range of social questions regarding the influence of contemporary society on literary fiction. Publications regarding this thesis is currently work in progress. 

Summary: Analyzing the writing styles of authors and articles is a key to supporting various stylometry analysis tasks such as author attribution, genre identification, etc. Consequently, social structures and real-world incidents often impact contemporary literary fiction. In this study, we perform literary analysis from both perspectives by solving stylometry tasks as well as incorporating character networks. Our study involves constructing character interaction graphs from fiction, extracting graph features, and exploiting these features to resolve these queries. Experimental evaluation of influential Bengali fiction over more than half a century demonstrates that character interaction graph can be highly effective in certain types of assessments and information retrieval from literary fiction. We also propose a novel word2vec graph based modeling of a story that can rightly capture both the context and the structure of the story. By using these word2vec graph based features, we develop a classification technique to perform several stylometry tasks: author attribution, genre detection, stylochronometry. Our detailed experimental study with a comprehensive set of literary writings from famous authors of Bengali literature shows the effectiveness of this method over traditional feature based approaches.

• Supervisor: Dr. Mohammed Eunus Ali

• Status: Two papers are achieved based on my M.Sc. thesis.

  • Nafis Irtiza Tripto and Mohammed Eunus Ali “Writing Style Analysis in Bengali Literature using W2V Graphs” (under review, Transactions of the Association for Computational Linguistics)

  • Nafis Irtiza Tripto and Mohammed Eunus Ali “Understanding Social Structures from Contemporary Literary  Fiction  using  Character  Interaction  Graph  -  Half  Century  Chronology  of  Influential Bengali Writers.” (under preparation for ICTD’22)

This was my undergraduate thesis topic in Department of CSE, BUET.  We  proposed and investigated the k Aggregate Maximum Visibility Trajectory (kAMVT) query and its variants. 

Summary: The recent advancement in large-scale 3D modeling has inspired applications that combine visibility and spatial queries, which in turn can be integrated with user trajectories to provide answers for many real-life user queries, such as “How can I choose the route which provides the best view of a historic site?”. In this work, we propose and investigate the k Aggregate Maximum Visibility Trajectory (kAMVT) query and its variants. Given sets of targets, obstacles, and trajectories, the kAMVT query finds top-k trajectories that provide the best view of the targets. To provide an efficient solution to our problem, we employ obstacle and trajectory pruning mechanisms. To verify the efficiency and effectiveness of our solutions, we conduct an extensive experimental study using large synthetic and real datasets.

• Supervisor: Dr. Mohammed Eunus Ali

• Status: Published in Geoinformatica Journal. I became a regional winner in Global Undergraduate Award in Computer Sciences Category  in 2018 by submitting this thesis. 

Nafis Irtiza Tripto, Mahjabin Nahar, Mohammed Eunus Ali, Farhana Murtaza Choudhury, J. Shane Culpepper, Timos Sellis, “Top-k trajectories with the best view”, GeoInformatica, 17, 2019. 

A CodeBlocks Plugin was developed to capture a coding snapshot of students and relevant logs when the program is compiled. Data from relevant programming sessional courses (C, C++, Data structure/Algorithm) were collected over two semesters in BUET. The primary motivation of the project is to identify how students in different courses and different departments come to the solution and what types of errors they make. This project was done as part of my Masters course: Software Quality Assurance.  I plan to extend the project with collaboration from other universities. 

• Supervisor: Dr. Anindya Iqbal  & Dr. Mohammad Saifur Rahman

We perform anomaly on time series gene expression using two deep learning based techniques and compare their performance with machine learning based method. Moreover, we apply deep learning based Neural Network and LSTM methods to forecast from previous values in gene expression and compare their performance with popular statistical method like ARIMA and Holtz Winter.

• Supervisor: Dr. Md. Shamsuzzoha Bayzid & Dr. Atif Hasan Rahman

• Status: Published in PLOS One Journal, 2021. 

Nafis Irtiza Tripto, Mohimenul Kabir, Md. Shamsuzzoha Bayzid, Atif Rahman, “Evaluation of classification and forecasting methods on time series gene expression data”, PLOS ONE, 15, e0241686, 2020.

The aim of the project is to build an artificial intelligence based Chatbot for medical support and communicate with users about adolescence, sexual and reproductive health. We have conducted a feasibility study among the adolescent community and developed a prototype version. We deployed the Chatbot as FB messenger Plugin.

• Supervisor: Dr. Mohammed Eunus Ali , Rifat Shahriyar

• Status: Published in CHI, 2021. 

Rifat Rahman, Md. Rishadur Rahman, Nafis Irtiza Tripto, Mohammed Eunus Ali, Sajid Hasan Apon, and Rifat Shahriyar. 2021. “AdolescentBot: Understanding the Opportunities for Chatbots in Combating Adolescent Sexual and Reproductive Health Problems in Bangladesh”. In CHI Conference on Human Factors in Computing Systems (CHI ’21), May 8–13, 2021, Yokohama, Japan.