I am a PhD candidate in Computer Science and Engineering at the University of Michigan, where I am a part of the LIT research group, supervised by Dr. Rada Mihalcea.

My research interests include natural language processing, machine learning, computational social science, word embeddings, word semantics, and data science.


Factors Influencing the Surprising Instability of Word Embeddings

Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea

PDF Code Poster Slides

Despite the recent popularity of word embedding methods, there is only a small body of work exploring the limitations of these representations. In this paper, we consider one aspect of embedding spaces, namely their stability. We show that even relatively high frequency words (100-200 occurrences) are often unstable. We provide empirical evidence for how various factors contribute to the stability of word embeddings, and we analyze the effects of stability on downstream tasks.

author = {Wendlandt, L. and J. Kummerfeld and R. Mihalcea},
title = {Factors Influencing the Surprising Instability of Word Embeddings},
journal = {NAACL-HLT},
year = {2018}

Viegas, Felipe, et al. "CluWords: Exploiting Semantic Word Clustering Representation for Enhanced Topic Modeling" Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. 2019.

Köper, Maximilian. Computational approaches for German particle verbs: compositionality, sense discrimination and non-literal language. Diss. Universität Stuttgart, 2018. Web. November 26, 2018.

Müller and Strube. "Transparent, Efficient, and Robust Word Embedding Access with WOMBAT." COLING: System Demonstrations. 2018.

Rogers, Anna, et al. "What’s in Your Embedding, And How It Predicts Task Performance." COLING. 2018.

Regneri, Michaela, et al. "Analyzing Hypersensitive AI: Instability in Corporate-Scale Machine Learning." IJCAI-ECAI Workshop on Explainable AI. 2018.

Karpinska, Marzena, et al. "Subcharacter Information in Japanese Embeddings: When Is It Worth It?" Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP (RepL4NLP). 2018.

Multimodal Analysis and Prediction of Latent User Dimensions

Laura Wendlandt, Rada Mihalcea, Ryan L. Boyd, James W. Pennebaker
SocInfo, 2017

PDF Code Poster Slides

Humans upload over 1.8 billion digital images to the internet each day, yet the relationship between the images that a person shares with others and his/her psychological characteristics remains poorly understood. In the current research, we analyze the relationship between images, captions, and the latent demographic/psychological dimensions of personality and gender. We consider a wide range of automatically extracted visual and textual features of images/captions that are shared by a large sample of individuals (N ~ 1,350). Using correlational methods, we identify several visual and textual properties that show strong relationships with individual differences between participants. Additionally, we explore the task of predicting user attributes using a multimodal approach that simultaneously leverages images and their captions. Results from these experiments suggest that images alone have significant predictive power and, additionally, multimodal methods outperform both visual features and textual features in isolation when attempting to predict individual differences.

author = {Wendlandt, L. and R. Mihalcea and R. Boyd and J. Pennebaker},
title = {Multimodal Analysis and Prediction of Latent User Dimensions},
booktitle = {Proceedings of the 9th International Conference on Social Informatics (SocInfo 2017)},
year = {2017},
address = {Oxford, UK}

Data Science in Service of Performing Arts: Applying Machine Learning to Predicting Audience Preferences

Jacob Abernethy, Cyrus Anderson, Chengyu Dai, John Dryden, Eric Schwartz, Wenbo Shen, Jonathan Stroud, Laura Wendlandt, Sheng Yang, Daniel Zhang
Bloomberg Data for Good Exchange, 2016


Performing arts organizations aim to enrich their communities through the arts. To do this, they strive to match their performance offerings to the taste of those communities. Success relies on understanding audience preference and predicting their behavior. Similar to most e-commerce or digital entertainment firms, arts presenters need to recommend the right performance to the right customer at the right time. As part of the Michigan Data Science Team (MDST), we partnered with the University Musical Society (UMS), a non-profit performing arts presenter housed in the University of Michigan, Ann Arbor. We are providing UMS with analysis and business intelligence, utilizing historical individual-level sales data. We built a recommendation system based on collaborative filtering, gaining insights into the artistic preferences of customers, along with the similarities between performances. To better understand audience behavior, we used statistical methods from customer-base analysis. We characterized customer heterogeneity via segmentation, and we modeled customer cohorts to understand and predict ticket purchasing patterns. Finally, we combined statistical modeling with natural language processing (NLP) to explore the impact of wording in program descriptions. These ongoing efforts provide a platform to launch targeted marketing campaigns, helping UMS carry out its mission by allocating its resources more efficiently. Celebrating its 138th season, UMS is a 2014 recipient of the National Medal of Arts, and it continues to enrich communities by connecting world-renowned artists with diverse audiences, especially students in their formative years. We aim to con tribute to that mission through data science and customer analytics.

author = {Abernethy, J. and C. Anderson and C. Dai and J. Dryden and E. Schwartz and W. Shen and J. Stroud and L. Wendlandt and S. Yang and D. Zhang},
title = {Data Science in Service of Performing Arts: Applying Machine Learning to Predicting Audience Preferences},
booktitle = {Bloomberg Data for Good Exchange},
year = {2016},


In addition to research, I enjoy teaching computer science. Selected relevant experience is listed below.

  • Primary instructor: EECS 198 - Discover CS (Fall 2018)
  • Co-instructor: EECS 498/595 - Natural Language Processing (Fall 2017)
  • Graduate Student Instructor: EECS 281 - Data Structures and Algorithms (Fall 2015, Winter 2016)
  • Python tutorial instructor at CS KickStart (Summer 2017)
  • Guest instructor for ICOS Big Data Summer Camp (2018)
  • Guest lecturer for EECS 486: Information Retrieval (2018)
  • Co-facilitator for "Making Teamwork Work" seminar, continuing education for student instructors through CRLT-Engin (Center for Research on Learning and Teaching in Engineering) (2018)
  • Teaching Assistant: CS and Physics classes at Grove City College (Fall 2012 - Spring 2015)
  • Personal Tutor: One-on-one tutor for students struggling in CS (Fall 2013 - Spring 2015)


My vision is to see computer science become a more diverse field where women and other underrepresented minorities have the tools and opportunities needed to succeed. Towards that end, I am interested in exploring creative solutions to both recruit and retain women in technology.

I am co-director of Girls Encoded, an initiative at the University of Michigan to improve the recruitment and retention of women and underrepresented minorities in computer science.

Through Girls Encoded, we introduced a new class in Fall 2018, EECS 198: Discover CS. This class is particularly designed to introduce incoming freshmen women to the excitement of programming for the first time.

In addition to Girls Encoded, I am involved in CS KickStart, a week-long summer program designed to help women explore computer science. I was one of the original organizers who brought this program to UM in August 2016. In addition, I handled industrial relations in 2016 and continued to serve as an advisor in 2017. In 2018, I was the primary Python tutorial instructor.

Blog Posts

Word Embeddings and How They Vary

Reflections on Telle Whitney Dow Lecture

Cool Things

Performance of Enchantress, an opera featuring Ada Lovelace (11/2017, UM)

Lightning talks by women computer science researchers at UM (11/2017)