classify me! why?

what is this?

Machine learning algorithms operate all around us, whether they recognize your face in a picture or show you ads for something that you might actually be tempted to buy. They control many aspects of our daily lives and make important decisions for us. Decisions we often may not understand. To uncover the inner workings of these algorithms, researchers at the Fraunhofer HHI and the Technische Universität Berlin developed a technique called Layer-wise Relevance Propagation (LRP), which can help to make classifier decisions more transparent.

This WebApp is designed to show you how LRP for text classification can work in practice - just play around with it below!

You can find more information about this particular example in this paper and further theoretical background on LRP in this paper or here.

For other projects from me visit my personal website.

try it for yourself:

Just input a paragraph from a scientific paper about cancer and see what our algorithm thinks is the type of cancer the paper is written about or from which section of the paper this paragraph was taken. And see why, i.e., which words tipped the classifier off.

Input text:

Fresh frozen breast cancer tissue from every third patient diagnosed and treated between 1991 and 2004 at the Koo Foundation Sun-Yat-Sen Cancer Center (KFSYSCC) were randomly selected for the study. Patients with follow-up periods shorter than three years were excluded, with the exception of those who died of the disease within three years of the initial treatment. In cases of ineligibility, the following sample was selected. The selected tissue samples spanned the major transition periods of adjuvant chemotherapy from CMF (cyclophosphamide, methotrexate and fluorouracil) to CAF (cyclophosphamide, doxorubicin, fluorouracil) and to taxane-based regimens. Four hundred forty seven samples were obtained, but 135 samples were excluded due to insufficient RNA (n = 1), poor RNA quality (n = 116), or unacceptable microarray quality (n = 18). A total of 312 samples were eligible for the study (Cohort 1). Gene expression profiles of an additional 15 lobular breast carcinoma samples, collected between 1999 and 2004 and previously studied, were also included (Cohort 2). All patients were treated by a multidisciplinary team according to the guidelines consistent with the National Comprehensive Cancer Network [18]. Following modified radical mastectomy or breast-conserving surgery plus dissection of axillary nodes, patients received radiotherapy, adjuvant chemotherapy, and/or hormonal therapy, if indicated. Neoadjuvant chemotherapy was administered to patients with locally advanced disease. The study was approved by the institutional review board (ID number 20020128A) and ethical approval was obtained from the same board for samples without obtainable informed consent.

classify me! why?

explaining machine learning text classification decisions

what is this?

try it for yourself:

Input text:

Classify: