Onegai! Pilgrimage to Lake Kizaki

Every anime fan who has been one longer than one boring summer will remember that very fateful moment when they have taken their red pill that set them tumbling down the rabbit hole of otaku obsessions. What instigated that moment for me was an anisong.

Seasonal anime offerings from summer 2003 weren’t that outstanding, with perhaps Full Metal Panic! Fumoffu? being the rare exception. Even though some might argue there was critical merit to Ikkitousen and Divergence Eve, for today’s standards they are run-of-the-mill shows at best. But it was a boring summer and people had to watch something. Personally, I got fixated on Onegai! Twins, which was your typical summer romance show. It featured a standard self-insertion protagonist and two cute girls. Drama ensues, shipping commences, with a potential ending involving a threesome looming over every fan’s mind. Of course, it was a wet dream. Drama gets resolved, best girl gets the protag’s dick, the loser gets to call him onii-chan. Nothing too crazy. I was more invested in the show because at the time I got an urge to translate some anime. I picked this one partially because a friend was already working on it for a release in a different target language. He helped me get started. But the reason why I even noticed the show was because I fucking fell in love with the opening song.

Second Flight was the brainchild of two very talented composers, Takase Kazuya and Nakazawa Tomoyuki. Takase is also president of I’ve Sound, a music label responsible for many of that day’s popular eroge songs, including theme songs for the Baldr games series. Many eroge sold on hype alone, of which I’ve Sound brought plenty to the table when it was on board. I was impressed porn could have pop songs that rivaled those playing on MTV. Even though they found niche success, the music collective produced minor stars such as Kotoko and Kawada Mami, with whom they released their songs under labels such as Lantis, Rondo Robe, Geneon Entertainment and Warner Bros Japan.

Please! was a media mix project centered mainly around two television anime, Onegai! Teacher, which was released in 2002, and the aforementioned Onegai! Twins. The latter wasn’t exactly a sequel, however main characters of both shows inhabited the same rural setting, with some side characters playing minor roles in both. There was another show released in 2012 titled Ano Natsu de Matteru, which was de facto a spiritual successor to the series. Even though it shared the same summer aesthetic and the same romance-with-a-girl-from-space theme as one of the previous two shows, I was bothered by the lack of a very specific ingredient that would have truly sold it for me.

It was the setting. NatsuMachi’s setting was modeled mostly after real locations from Matsumoto city. Teacher and Twins had a few of those taken there, notably for the school and for the romantic observatory, but the majority of their background scenery was taken from locations around the beautiful lake Kizaki, which lies around 30 kilometers north of Matsumoto. Not to take anything away from Matsumoto, but my nostalgia wasn’t being fueled by it, and so NatsuMachi kind of ruined the whole spiritual successor thing for me.

I’m not sure anymore when I discovered that Kizaki was not just an abstract ideal of summer Japanese beauty but an actual, geographical place. When I did, however, I took a vow to visit if a chance to travel to Japan should arise. I managed to do so a few days ago.

Please! Twins House
The House

The intro above starts with the three main characters noticing a particular house that was being shown on television. As far as I can guess, the exterior of the house is a patchwork of different houses from the same neighborhood, but the model location with a house similar to the one in the anime does exist. The angle from the road above the house, along with the neighbor’s view pretty much confirm it as the real deal.

Please! Twins House Road
View from the road coming toward the House
Please! Twins House Neighbor
View from the neighbor’s drive-in, denied

The nice Kotoko opening starts and we’re treated to the location below. For the longest time I thought this was a mountain road, but as it turns out it’s a walking trail along the lake’s eastern bank. The white fence on the left separates the trail from the lake.

Please! Twins Bank
Walking trail along the lake’s shore

Next up is the park, which is located behind a motorboat rental shop and restaurant. It’s where I purchased a plate of “Marie TWINS” curry and a bowl of “Fushigi-chan” ice cream. The benches, the swings, and the children’s slide are all at the same spot.

Please! Twins Park Benches
The lake is hiding behind the swampy plants
Please! Twins Park Swings
In the cropped-out foreground there was another swing

Facing the House right across the lake is a railroad crossing. I’ve got lucky snapping this one just as the Oito Line was active. I definitely recommend accessing the valley with the train from Itoigawa for the scenic views. Train otaku were aboard as well, which is enough of a confirmation for me that the ride has built itself a reputation.

Please! Twins Line Crossing
Right next to the famous Uminokuchi Station

And finally, the Slide. There was this foreigner right next to me, if you can believe it, that volunteered to have a few awkward poses taken wearing an Onegai! Teacher T-shirt. What a nice and handsome guy he was.

Please! Twins Park Slide
I had to wait some before taking this one, children were playing

Obviously I have more photos of other locations, some even that were specific to Onegai! Teacher, but I’m saving them for a special occasion. You should definitely check out a few photo galleries of other pilgrims who visited before me, like this one. Some of them came more prepared than I did; I was working the field with a mere phone camera. Though let it be known, I visited the same locations. Some of the pictures require breaking trespassing laws. If you decide to go on a pilgrimage, don’t do that. Then again, me loitering around the House while the owners were at home can’t be socially acceptable behavior either.

The series’ locations are great for beginner pilgrims. Do your research, rewatch the shows, take your own screenshots. And for God’s sake don’t look at the maps with Google Street View beforehand; you might as well be spoiling yourself. Take a walk around the lake, it will take you maybe two leisurely hours. You’ll find pretty much every location there is with ease. Local residents are friendly and helpful. They know what we come there for anyway. Visit Herikawa Shop, it truly exists. Stop by all three of the train stations near the lake. You can write down how much you love anime in their log books.

The weather did screw up my schedule to visit Matsumoto, but I’ll live. I don’t like the stay in Japan as much as I thought I would, mostly because of the oven-like heat and me naturally sweating like a pig, but Kizaki alone made the whole visit worth it. Next time I visit it’ll be me taking my future kids camping there, but I’m looking forward to it already.

Comic Market 90 Impressions

It’s my first visit to Japan and so it was natural to attend Comike as well, which ended just a few hours ago. Seeing Tokyo Big Sight for the first time up close in person was a bit overwhelming, I honestly didn’t expect it. But I put off this moment for far too long, I’m glad I finally decided to go.

Everything about the event is true. The crowds are so big it’s hard to imagine, yet human traffic stayed orderly on the premises and all the way along the Rinkai train line. Porn and PG-13 content balance each other out, with the latter having more interesting stuff to look at. I’m sad I didn’t take a proper photo of Arduino and other boards with VOCALOID characters printed on them, it was the coolest shit ever.

Also, Comic Market history records don’t lie – both men and women are equally represented at the event.

The cosplayers, I didn’t pay much attention to them, but people who are into that around here appreciate a very strange aesthetic. Most professional-looking cosplays – the ones every other Japanese cosplayer aspires to reach – were just boring (see here). You had perfect replications of fictional characters on a human body, yet they all looked so jarring. Perhaps they got too close to uncanny valley? Perfect cosplay like that can hardly fall under cuteness aesthetics of Japan. This is something I’ll have to think more about.

More on matters of porn, works like Genshiken and recently SaeKano have helped to create an image of a Japanese otaku who doesn’t judge others for their unorthodox tastes, because hey we all have a kinky fetish or two, right? However, I’ve overheard enough “kimochi waruis” in porn sections of East Hall to say that there is no respect. Japanese otaku just keep their opinions to themselves a bit more than their western counterparts do. But I guess that’s as much as you can expect from society.

Other than that, it’s an event for mostly shopping and small talk with creators, so it’s hard to say it’s otaku paradise. Industry booths had new anime trailers and lots of overpriced merchandise, but you know all that already. The people that make the event, the creators, cosplayers, and volunteers have the most fun, and unless you have a battle plan ready and lots of cash to spend – basically you create a game for yourself – Comike might as well just be an overcrowded shopping mall.

I was moved, impressed and disillusioned by the event all at once. But I’ll probably go again, next time paying more attention to circles of interest prior to the event.

Anime Fandom Has Lost Its Compass

The recent decades of anime and manga outside of Japan are characterized by the struggle to gain overseas popularity and to capture the imagination of western literary criticism. Throughout the years the fandom was put under pressure to develop mechanisms for fending off against the prejudices fueled by past Japanese-American relations and the cultural legacy of cartoons being degraded to children’s entertainment. Indeed, history doesn’t look all that pretty, but ultimately the push against the current bore success.

These days anime and manga have small, but vibrant industries in the western world, providing overseas fans fast and high-quality releases, which are now being streamed on major distribution platforms such as YouTube, Netflix, and Hulu. Business is booming, as is awareness of the medium. Everybody knows what the word anime means, and being a nerd who watches anime among other nerdy things has become sort of fashionable. Fans don’t have to struggle anymore by scavenging for subtitled copies in small comic book shops. We don’t have to camp obscure IRC channels for digital copies anymore, or send money to strange men living in basements with the hope of them returning a working, subtitled VHS copy. We can simply open a video app instead and have whatever we want to watch running on our mobile screens in seconds.

Being a fan of anime is pretty awesome these days. We are getting all these cool new shows and the library of timeless classics is constantly growing. I mean, who wants to go back to meager offerings of the past and poor accessibility? Obviously nobody. However, I do feel that being a fan in those days had its own charm. It was a hobby that forced you to socialize if you wanted your anime fix, which is quite different from these days. Think about that, you had to put in some effort to be able to watch anime. Sticking to the past isn’t desirable for a plethora of reasons, but I do feel that the hobby lost something in the process of shedding the inconveniences. Now that anime is easier to access than ever before, and all the knowledge a regular anime fan wants is right there on various wiki sites, what point is there besides endless consumption? What challenge is the medium going to throw at us next?

I believe that in the past anime fandom shared a common goal. To boil it down, we wanted to make anime more popular so as to benefit from that, but it was a struggle. Every fan of my generation can recall a personal story how he or she needed to explain herself to a layman why she loved what she loved, why this pursuit was no more childish than indulging in other types of entertainment, or why it wasn’t a waste of time. On the other hand, anime and manga’s worldwide accessibility was for the longest time shouldered by fansubbers and hackers, fans themselves, so to speak. I was part of this collective for a few years, and I can vouch that the amount of time and effort that went into fan translating anime almost felt like a full-time job at times. The persecution complex was also strong in our circles, which might have been due to the anti-piracy narrative that was at its strongest a decade ago, or perhaps due to the tight-knit relationship fans had with anime licensing companies. Despite the risks we knew we were on the right side of history, and so we kept on translating and kept on downloading with even more valor.

Another avenue of appeal stemmed from the fact that these mediums stayed mystified for a very long time, no thanks to fans that weren’t very methodical in pursuing knowledge about them, spreading misinformation and folklore along the way. It has taken several generations of Japanese linguistic studies graduates to become quite decent at translating Japanese media. Academia has also started taking a keen interest in them, carefully examining the state of things and clearing up some of the misconceptions that persisted throughout the decades. One misconception that is still relatively prevalent among fans even to this day is that anime is widely appreciated in Japan. Historical record has been set straight for the most part, facts published on Wikipedia with proper sourcing, and so on. Anime and manga have through proper translation practices and research lost most of their exoticism.

Miyazaki Hayao winning an Oscar for Best Animation was an event that ultimately led to the current situation in the West. Corporations have taken over translation and knowledge creation, and so us fans are left with the job of merely consuming the content. We don’t run anime clubs anymore with the intent of promoting anime and spreading otaku knowledge, because anime are popular enough on their own, while the clubs themselves turned into awkward social hubs with no creative output.

I thought long and hard what the “grand narrative” for western anime fandom was supposed to be this decade, what characterizes this generation apart from popular titles, where the “class struggle” lies in and all of that, but I simply can’t see it. Anime fandom these days is just one large parade toward adulthood, whilst older otaku are left to their own private interests. Even us bloggers used to think we were making a difference by writing passionate posts about anime, evangelizing everything that was interesting about the medium and our fandom. But whenever someone tries to do that these days, I start to wonder for how long have we been preaching to the choir.

Anime has become popular! So what are we supposed to be doing now?

Taking a Dump on Mayoiga

I’d like to share a bunch of Tweets that I made after the first episode’s broadcast.

Obvious is one word that perfectly describes Mayoiga. It’s certainly given us drama, but we’re not getting any blood. I mean, who honestly thought Yottsun was dead? Get literate.

Personally, I believe the show was originally conceived as a healing-type anime, aimed at confused teenagers, disillusioned young adults, and people with mental health problems, groups that are well represented among anime fandom. Then Okada came on board and turned this project into a communication anime. Is the audience actually capable of identifying with at least one character from the thirty-odd cast of fuckups? I don’t believe so. But the craziness is enough to get you guys talking about the show. For those who aren’t familiar with communication anime, their point is to create as many new camaraderies among fans, either through clash or cohesion of opinions in online discussions, forming a feeling of shared experience. Basically, everything goes as long as the show trolls as many people into the discussion as possible.

People are creating buzz and having fun, even myself, so where’s the harm? Well, one thing I noticed about these shows is that they tend to have really bad execution. Priorities change when it’s buzz that keeps a production profitable. But the problem is fans aren’t really having fun with the show presented to them. They are having fun talking to each other, and not necessarily about the show itself. After the first few episodes, the show becomes an afterthought. Sure, people still watch it but how many actually like the show for its own strengths? Repeat this a few times with a dozen bad, but popular shows, and kids will realize they don’t need an excuse to hang out with other fans. The lack of outstanding qualities may turn them off from watching anime altogether.

That’s possibly one of the major reasons why anime fandom has such low retention rates.

Fans probably won’t be standing in line to buy this gem on home video, but I’m sure a sizable portion of them bought into the idea that everybody should visit the hidden village for themselves and accept their Nanaki.

Expect real-life bus tours of model villages running throughout the summer. Because making pseudo-friends on sketchy bus tours is what being an anime fan is all about.

MAL’s Most Popular TV Anime Genres

It’s not easy finding an anime show that can be tagged with a single genre. Comedies are almost always romances, and shows portraying school life are almost never about students sitting behind their desks. It’s either mysteries or sports clubs or students fighting other students in exoskeletons or giant robots. So if I say that school life is the most popular genre on MAL, of course you can believe me, then again that tells you almost nothing of the type of anime that dominant fan groups like to watch.

This is a follow-up to my exploration of AniDB’s genre tags. The idea was to take a look at crowdsourced data and see which genres usually stick together. The previous time I basically downloaded info from AniDB about every TV anime starting sometime in the last five years. I calculated how similar anime shows were among themselves in terms of genre information and grouped them accordingly. I was hoping that this grouping would correlate well with how popular the grouped anime are, and while I think the results were aiming in the right direction, I started questioning my methodology and my data source.

This time I tried doing the same, except that I used MyAnimeList’s data. I also changed my approach to similarity scores. Instead of using cosine similarity, which didn’t make much sense from a theoretical standpoint, I employed Jaccard similarity coefficient, which can be used for unweighted genre information. What is Jaccard similarity? Basically, if you have two anime that have the same subset of genres, then their Jaccard similarity score will be the number of genres in this subset divided by the number of genres presented by both. Do this pairwise for every two anime and you get a nice similarity matrix that we can run a clustering algorithm on. This algorithm spits out a grouping of anime titles, which enables us to check which genres are the most popular in each group. Below I present the results of this clustering procedure.

Results

TV Anime Group 1
Titles: 136
Average voters: 57332
Most common genres: 
    1.  comedy           (128 titles)
    2.  school           (118 titles)
    3.  romance          (86 titles)
    4.  shounen          (51 titles)
    5.  ecchi            (48 titles)
    6.  harem            (42 titles)
    7.  supernatural     (28 titles)
    8.  action           (23 titles)

TV Anime Group 2
Titles: 149
Average voters: 57040
Most common genres: 
    1.  action           (145 titles)
    2.  fantasy          (101 titles)
    3.  shounen          (72 titles)
    4.  adventure        (61 titles)
    5.  supernatural     (48 titles)
    6.  comedy           (48 titles)
    7.  magic            (33 titles)
    8.  game             (21 titles)

TV Anime Group 3
Titles: 125
Average voters: 43241
Most common genres: 
    1.  action           (117 titles)
    2.  sci-fi           (72 titles)
    3.  mecha            (37 titles)
    4.  seinen           (26 titles)
    5.  drama            (20 titles)
    6.  super power      (18 titles)
    7.  supernatural     (16 titles)
    8.  adventure        (14 titles)

TV Anime Group 4
Titles: 184
Average voters: 33462
Most common genres: 
    1.  school           (49 titles)
    2.  drama            (43 titles)
    3.  slice of life    (43 titles)
    4.  romance          (40 titles)
    5.  fantasy          (37 titles)
    6.  shoujo           (32 titles)
    7.  supernatural     (31 titles)
    8.  mystery          (26 titles)

TV Anime Group 5
Titles: 110
Average voters: 25340
Most common genres: 
    1.  slice of life    (110 titles)
    2.  comedy           (109 titles)
    3.  school           (46 titles)
    4.  seinen           (27 titles)
    5.  shounen          (8 titles)
    6.  romance          (7 titles)
    7.  drama            (5 titles)
    8.  fantasy          (5 titles)

TV Anime Group 6
Titles: 142
Average voters: 21975
Most common genres: 
    1.  comedy           (142 titles)
    2.  supernatural     (27 titles)
    3.  shounen          (22 titles)
    4.  fantasy          (21 titles)
    5.  mystery          (16 titles)
    6.  romance          (16 titles)
    7.  action           (14 titles)
    8.  drama            (14 titles)

Methodology

I was working with 846 anime titles and 40 different genre tags. This time I paid special attention to the number of clusters. Because it’s hard to say what the correct number of clusters is (it could be just one, it could be 846 of them), unless certain metrics show solid numbers, such as the silhouette score from the previous time, you have to ask yourself what types of anime should these clusters be having. We obviously want as little clusters as possible so that we can generalize well, while at the same time we want to see popular anime grouped in their own clusters, respective of each title’s genre similarities above all else.

Alongside the anime’s average user rating MAL also lists the number of votes each title has. Casting a vote is an expression of emotional involvement. Proof of this is that the vote count is relatively higher for very good shows and for very bad shows. We can exploit this property and say that shows with a higher vote count were also, most likely, the most watched.

Therefore we model the number of anime clusters along this number. We look at the clusters’ vote count averages and try to maximize them for each cluster by either lowering or increasing the number of clusters. Anime may fall into different clusters as we increase their number, and so too will their respective vote counts.

There was more sorcery involved, but ultimately I settled on there being six clusters that you can see above. Some have less popular importance than others, that’s because popular importance is based on the aforementioned vote count average.

This optimization problem wasn’t a cakewalk, then again I didn’t bother with any mathematical procedure for it. I settled on analyzing the means and medians with the eyeball method. Ask if you want me to go into more detail, but I doubt you do. Also, I had to do some scripting to make all of this work in the first place. Code will be made available sometime in the future.

Conclusion

I still think AniDB’s tagging system is better, because they have over 180 tags, whereas MAL has only 40 or something. AniDB also lets users place a weight for each tag. Unfortunately these become improvements only with more active users, which AniDB compared to MAL doesn’t have. What the future has in store for this experiment, it’s hard to say, but for it to have the best conditions one would need to build a better, more detailed, and more popular anime database. Contact me if you’re into that kind of thing.

My Top Anime 3×3

I hear kids these days make these collages to show off their taste in anime. Welp, guess what I’ve spent working on this past Saturday. At first I wanted to make one off the top of my head, but I soon found myself browsing through old anime seasons. Before I knew it the day was over and I’ve built a shortlist that you can’t go wrong with. But I had to choose a handful and this is what I came up with.

Top 9 Anime
My hesitantly chosen Top 9 Anime Shows of All Time

A couple of points:

  • While browsing old seasons, I took notice of this show called Avenger from 2003. I wasn’t that averse to Bee Train’s shooters, but that one was probably the worst. I made Madlax a candidate though.
  • Another thing that I was reminded of was that I liked Suzumiya Haruhi only in the heat of the biggest hype. The boring DVD watch order embodies this sentiment perfectly.
  • I rewatched Howl’s Moving Castle yesterday. I was about to put it on the 3×3, but knowing recency bias might be in play convinced me otherwise. I probably made a bad decision. Hosoda’s Summer Wars didn’t come close. Shinkai’s films didn’t make the shortlist. So much for feature-length films.
  • Yes, that’s the Toei version of Kanon. Don’t listen to the talking heads, Shingetsutan Tsukihime was a best-seller. Black History is a lie.

That’s about it. Oh, and for the record, my heart broke when I decided to cut Chihayafuru. It was a tough call.

What Anime Genres Do We Like Watching These Days?

This is another one of my data posts. You have been warned.

MDS Plot
MDS visualization of major anime groups today, presented in 2D!

I noticed an interesting question on one of the online anime places that I frequent: What types of anime shows are being made these days? Some folks wanted to do a statistical analysis on the matter, but merely counting genres is easy and that’s boring.

So I came up with a new question. Given that people like watching certain genres more often than other, what genres do we like watching these days on the whole? By that I mean things like, what does the dominant fan group watch, and is my taste still relevant to anime producers?

If I was going to do this, first thing I needed to do was to tap into an anime data source! I was already familiar with AnimeNewsNetwork, AniDB and TV Tropes, but I also wanted to check out this Japanese website called AniKore, where users are encouraged to vote on user-submitted tags. I would have produced a nicely weighted dataset from those, but unfortunately AniKore’s top-ranking tags simply suck. Too many titles have dumb qualitative descriptors tacked onto them, such as kami anime (tl: God-tier anime) that tell you absolutely nothing about the kind of anime you’re dealing with. The problem with TV Tropes, on the other hand, is that their tags aren’t general enough, which is an understatement of the century. Then again, ANN’s genres are too general. Luckily AniDB offered a nice middle ground between the two extremes, with a total of 140 different genre tags.

I don’t want to bore you guys too much with all the technicalities and math that went into this. You can just skip down to the results. Let me just state for the record what general steps I took so that this won’t seem like complete voodoo magic.

  1. I extracted title, start date, ranking, vote count and tag information from AniDB for nearly every TV anime show since the start of 2011 up to this season.
  2. I noted which tags belong to which anime, then I compared numerical representations of anime between each other and produced so-called cosine similarity measures for all pairs of anime. Thusly, each anime pair got scored on how similar they were, or weren’t.
  3. I ran a clustering algorithm on all the scores, which spat out the four groups of anime it thought looked similar to one another. Clustering algorithms try to group similar items along a certain similarity measure. In our case that was cosine similarity.
  4. I counted which tags are the most common for each of the four groups. I also measured how many users voted on average and what their average user rating was inside each group.

You can verify my methodology in the code that I posted on Github. Did this procedure lead to any fruitful results? You decide.

Results

Anime Group 1
Members:  169
Group average ranking:  4.4
Group average voters:  649
Most common tags:
    1.    new                  (anime with this tag: 169)
    2.    science fiction      (anime with this tag: 50)
    3.    comedy               (anime with this tag: 38)
    4.    action               (anime with this tag: 36)
    5.    mecha                (anime with this tag: 35)
    6.    short episodes       (anime with this tag: 30)
    7.    seinen               (anime with this tag: 26)
    8.    fantasy              (anime with this tag: 22)
    9.    super power          (anime with this tag: 21)
   10.    shounen              (anime with this tag: 19)

Anime Group 2
Members:  129
Group average ranking:  3.38
Group average voters:  336
Most common tags:
    1.    game                 (anime with this tag: 72)
    2.    visual novel         (anime with this tag: 29)
    3.    bishounen            (anime with this tag: 18)
    4.    short episodes       (anime with this tag: 16)
    5.    science fiction      (anime with this tag: 16)
    6.    RPG                  (anime with this tag: 15)
    7.    action               (anime with this tag: 15)
    8.    shoujo               (anime with this tag: 15)
    9.    shounen              (anime with this tag: 14)
   10.    music                (anime with this tag: 14)

Anime Group 3
Members:  355
Group average ranking:  5.27
Group average voters:  792
Most common tags:
    1.    manga                (anime with this tag: 344)
    2.    comedy               (anime with this tag: 189)
    3.    shounen              (anime with this tag: 136)
    4.    seinen               (anime with this tag: 118)
    5.    daily life           (anime with this tag: 82)
    6.    short episodes       (anime with this tag: 77)
    7.    school life          (anime with this tag: 70)
    8.    action               (anime with this tag: 59)
    9.    4-koma               (anime with this tag: 55)
   10.    fantasy              (anime with this tag: 53)

Anime Group 4
Members:  195
Group average ranking:  4.93
Group average voters: 1353
Most common tags:
    1.    novel                (anime with this tag: 142)
    2.    fantasy              (anime with this tag: 107)
    3.    seinen               (anime with this tag: 103)
    4.    action               (anime with this tag: 93)
    5.    comedy               (anime with this tag: 82)
    6.    harem                (anime with this tag: 63)
    7.    school life          (anime with this tag: 56)
    8.    ecchi                (anime with this tag: 55)
    9.    romance              (anime with this tag: 46)
   10.    contemporary fantasy (anime with this tag: 42)

A few general observations on my behalf:

  • It seems like Group 2 crowns itself with the genre that has traditionally the worst reputation for adaptations – games.
  • The clustering algorithm was adamant to put game adaptations, manga adaptations, original anime, and novel adaptations into separate groups. Does the source medium really have such a draw for certain other genres or is that more an influence from the algorithm itself?
  • Group 3 looks the strongest by average ranking, but personally I’d take a closer look at Group 4 if I wanted to know what kind of anime people love watching (and voting on) the most these days.
  • Let it be known that distances between each anime were derived only from genre existences and nothing else.

There you have it! If somebody knows a good weighting scheme for binary features, I’d appreciate the tip immensely. As always, comments are appreciated.