Join top gaming executives at GamesBeat Summit 2023, May 22-23 in Los Angeles. Register here.
Square Enix recently released a free game on Steam titled Square Enix Test Preview: The Portopia Serial Murder Case. This remake of a 1983 text-based adventure game used Natural Language Processing (NLP) to address what the publishers saw as limitations in the game’s original input-based gameplay. However, users are not happy with this new feature, to say the least.
NLP is a form of artificial intelligence that helps machines understand natural or conversational language. Reviews of the game show that Portopia, on the other hand, isn’t a good demonstration of this technology, if only because it doesn’t seem to understand natural language. This seems to suggest that even if AI and NLP can be used in games, it’s still not where it should be – at least in terms of how much agency its creator is willing to give the player.
What is the Portopia serial murder case?
The Portopia Serial Murder Case is a crime adventure, one of the most influential games in the visual novel and 2D adventure genres. It was originally developed by Yuji Horii and published by Enix, one of the predecessors of modern Square Enix. In it, the player takes on the role of a detective trying to solve a murder in 1980s Japan with the help of his partner, and most of the game consists of bossing him around. This Technical Preview is the first English language release of Portopia.
As Square Enix explains, the original version of the game relied on “command prompts,” which required players to type commands into the game. The site acknowledges the limitations: “However, they shared a common source of frustration: players who knew what action they wanted to take were unable to do so because they couldn’t find the right wording. This problem was caused by the limitations of PC performance and NLP technology of the time.”
case
GamesBeat Summit 2023
Join the GamesBeat community in Los Angeles May 22-23. You hear from the brightest minds in gaming to share their updates on the latest developments.
Register here
The updated Portopia port does not dispense with command prompts entirely. Instead, it attempts to use NLP to make it easier for players to convey the commands. The company says Natural Language Understanding (NLU) is used in the game “to help the junior detective understand the player’s instructions.” In theory, this would allow users to get the answer they want, even if theirs command is not exactly what the game expects.
It seems that NLP has not solved the problem as well as the editor had hoped. At the time of writing this article, the rating of the game on Steam is “Very Poor”. The general temperature from the reviews is that the technical preview and natural language processing don’t seem to understand natural language. Often players had to simplify their language as much as possible so that the game understood what they wanted to do.
So what went wrong?
Reviews of the game on Steam show that the game often misunderstands or ignores commands, although they differ only slightly from the one you want. The AI seems to be splitting hairs. If they don’t understand what you’re saying, your in-game partner will respond by telling you, the detective, to focus on the task at hand.
One of the reasons this seems to have failed is that Portopia doesn’t offer much text-based freedom. The player must follow the story dictated by the game. All inputs must always be guessed until the player hits the right one, and the game will not progress until he does so. As such, the developers can’t give players much leverage over their own speech – they “have to” say a specific thing to advance the plot.
As an example of NLP being used successfully in another type of game, a 2005 game called Facade used AI to tell a story in which the player was an active agent. They could say whatever they wanted and the characters in the game would react accordingly. Even if the player didn’t type in a specific sentence, the game’s two characters can still get the gist thanks to the game’s NLP. This gives the player the freedom to explore their options, and the story continues even if the game doesn’t fully understand the player.
Last but not least, this seems to show that AI, or at least natural language processing, will not always work in all games. Visual novels don’t give players much leeway. Unlike Facade, Portopia cannot allow the player to say and do as they please. Therefore, the AI in the game can only react to certain phrases. But even within these limitations, Portopia’s NLP seems immature and unpolished.
GamesBeat’s credo when covering the gaming industry is “Where passion meets business”. What does that mean? We want to tell you how important news is to you – not only as a decision maker in a game studio, but also as a fan of games. Whether you read our articles, listen to our podcasts, or watch our videos, GamesBeat will help you learn more about and enjoy engaging with the industry. Discover our briefings.
