Introduction []
Essay Helper is a GitHub Repository written in SWI-Prolog that helps write the introduction, exposition, critique and conclusion of a humanities essay given an essay to write on. The algorithm uses KNN to detect reused sentences, for example in comments and connections. It uses a positivity checker that requires all sentences to contain only positive terms, sometimes except critique comments and connections.
The algorithm repeats asking for reason data if the user enters data that fails, for example if it can't recognise reused phrases.
KNN Limitations []
The algorithm uses the K-Nearest-Neighbour algorithm which recognises the identical phrase and the phrase with only the first word changed, but fails if replacements or deletions involving multiple words are made at the start of the phrase. It can fail when trying to recognise the phrase with only the first word changed if there is another change.
Positivity Checker and Implications []
Because the essay helper requires positive terms in the exposition, the user can't fail the assignment. Because the essay is correctly structured, the user can't earn a mark lower than D (65%). Because the user must breason out and hand in the first 80 breasonings, the user can't earn a mark lower than B (75%). The user will earn 80% if he agrees and 75% if he disagrees.
Random writing of essays[]
Essay Helper 3 automatically outputs the essay in HTML form, traversing the argument in a tree structure. In addition, Essay Helper 3.1 chooses sentences containing any given keywords. The random essay generator overcomes ethical concerns because it helps students of long-term degrees overcome stress from writing essays. It prevents repeating sentences multiple times in the essay.
New versions of 3 include [vague] Mind Reading and Chicago style (famous for the Ibidem feature), which is added to AGPS style.
Source Tagger[]
Source Tagger is an algorithm in the Essay Helper Repository that manages a database of tags, texts and references, and searches for queries containing tags. Source Tagger 2, which searches for multiple tags at the same time is in the Philosophy Repository. Source Tagger 3, which will enable Essay Helper to automatically create tags from sources and keywords, ask the user to assign themes to tags and cross-themes to themes, is planned.
Fast Mind Reader and Mind Reader Tree[]
Fast Mind Reader selects from a list of whole options, i.e. "apple" or "ant". Detailed mind reader tree allows selection of choice-points through sentences. e.g. "a", then "p" or "n", etc. Fast mind reader and mind reader tree have error catching code for stability.
Future Features []
- Changing from KNN machine learning to an algorithm that captures all possible paraphrasings
- Automatic breasoning (outputs breasoning dictionary only for the essay) and marking.
References []
Results of Various Tests of K-Nearest-Neighbour to Recognise a Paraphrased Statement